How to visualize activations of leayers in tensorlow?

Question

I am trying to visualize activation of layers in my model, but got a value error calling:

ValueError: Graph disconnected: cannot obtain value for tensor KerasTensor(type_spec=TensorSpec(shape=(None, 128, 128, 3), dtype=tf.float32, name='input_1'), name='input_1', description="created by layer 'input_1'") at layer "conv1_pad". The following previous layers were accessed without issue: []

when I was trying:

activation_model = Model(inputs = model.input, outputs = layer_outputs)

Following is my code

from tensorflow.keras.preprocessing import image
import numpy as np

# Pre-processing the image
img = image.load_img("fluidsets/1VS1/177.jpg", target_size = (128, 128))
img_tensor = image.img_to_array(img)
img_tensor = np.expand_dims(img_tensor, axis = 0)
img_tensor = img_tensor / 255.

# Print image tensor shape
print(img_tensor.shape)

# Print image
# import matplotlib.pyplot as plt
# plt.imshow(img_tensor[0])
# plt.show()
# Outputs of the 8 layers, which include conv2D and max pooling layers
layer_outputs = [layer.output for layer in model.layers[:8]]
activation_model = Model(inputs = model.input, outputs = layer_outputs)
activations = activation_model.predict(img_tensor)

# Getting Activations of first layer
first_layer_activation = activations[0]

# shape of first layer activation
print(first_layer_activation.shape)

# 6th channel of the image after first layer of convolution is applied
plt.matshow(first_layer_activation[0, :, :, 6], cmap ='viridis')

# 15th channel of the image after first layer of convolution is applied
plt.matshow(first_layer_activation[0, :, :, 15], cmap ='viridis')

This is the detail of my model

Model: "model"
_________________________________________________________________
 Layer (type)                Output Shape              Param #   
=================================================================
 input_2 (InputLayer)        [(None, 128, 128, 3)]     0         
                                                                 
 sequential (Sequential)     (None, 128, 128, 3)       0         
                                                                 
 tf.__operators__.getitem (S  (None, 128, 128, 3)      0         
 licingOpLambda)                                                 
                                                                 
 tf.nn.bias_add (TFOpLambda)  (None, 128, 128, 3)      0         
                                                                 
 resnet50 (Functional)       (None, 4, 4, 2048)        23587712  
                                                                 
 global_average_pooling2d (G  (None, 2048)             0         
 lobalAveragePooling2D)                                          
                                                                 
 dropout (Dropout)           (None, 2048)              0         
                                                                 
 dense (Dense)               (None, 5)                 10245     
                                                                 
=================================================================
Total params: 23,597,957
Trainable params: 10,245
Non-trainable params: 23,587,712