question about method `measure_idc`

[Jacob-yen]

@hasanferit @gerasimou
First and foremost, thanks so much for sharing the code! ：）
I have a question about method measure_idc when I read the source code.
At the beginning of measure_idc, variable subject_layer(the index of the subject layer from which we get relevant neuron) is reassigned as subject_layer - 1

deepimportance_code_release/coverages/idc.py

Lines 256 to 262 in 62bea40

	def measure_idc(model, model_name, test_inputs, subject_layer,
	relevant_neurons, sel_class,
	test_layer_outs, qtized, is_conv,
	covered_combinations=()):
	subject_layer = subject_layer - 1
	for test_idx in range(len(test_inputs)):

Later in method measure_idc, the new subject_layer is used to get the output of the "subject layer".

deepimportance_code_release/coverages/idc.py

Lines 265 to 268 in 62bea40

	for r in relevant_neurons:
	lout.append(np.mean(test_layer_outs[subject_layer][test_idx][...,r]))
	else:
	lout = test_layer_outs[subject_layer][test_idx][relevant_neurons]

It seems that we get the relevant neurons of the subject layer(with index subject_layer), but we use the outputs of subject_layer - 1 layer to calculate the idc. That makes me really confused.
Please point out if I misunderstand the code.

I would like to thank you in advance for your time and look forward to hearing from you.