Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2724 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.6155. Min Range: -3.6155
Max Act: 3.6155. Min Act: -0.1700
Data Index: 3789211 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6155. Min Range: -3.6155
Max Act: 3.4902. Min Act: -0.1700
Data Index: 5194280 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6155. Min Range: -3.6155
Max Act: 3.4902. Min Act: -0.1700
Data Index: 6187791 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6155. Min Range: -3.6155
Max Act: 3.4902. Min Act: -0.1700
Data Index: 3377712 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6155. Min Range: -3.6155
Max Act: 3.4589. Min Act: -0.1700
Data Index: 5539782 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6155. Min Range: -3.6155
Max Act: 3.4589. Min Act: -0.1700
Data Index: 6296372 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6155. Min Range: -3.6155
Max Act: 3.4589. Min Act: -0.1700
Data Index: 457439 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6155. Min Range: -3.6155
Max Act: 3.3962. Min Act: -0.1700
Data Index: 7544446 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6155. Min Range: -3.6155
Max Act: 3.3962. Min Act: -0.1700
Data Index: 8701308 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6155. Min Range: -3.6155
Max Act: 3.3962. Min Act: -0.1700
Data Index: 4801599 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6155. Min Range: -3.6155
Max Act: 3.3962. Min Act: -0.1700
Data Index: 1315904 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6155. Min Range: -3.6155
Max Act: 3.3648. Min Act: -0.1700
Data Index: 2890754 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6155. Min Range: -3.6155
Max Act: 3.3334. Min Act: -0.1699
Data Index: 5158014 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6155. Min Range: -3.6155
Max Act: 3.3020. Min Act: -0.1700
Data Index: 8655940 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6155. Min Range: -3.6155
Max Act: 3.2706. Min Act: -0.1699
Data Index: 4106213 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6155. Min Range: -3.6155
Max Act: 3.2706. Min Act: -0.1700
Data Index: 4397702 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6155. Min Range: -3.6155
Max Act: 3.2706. Min Act: -0.1700
Data Index: 8375864 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6155. Min Range: -3.6155
Max Act: 3.2392. Min Act: -0.1700
Data Index: 1647871 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6155. Min Range: -3.6155
Max Act: 3.2392. Min Act: -0.1700
Data Index: 2472293 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6155. Min Range: -3.6155
Max Act: 3.2392. Min Act: -0.1700
Data Index: 2158164 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19