Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 901 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.4018. Min Range: -7.4018
Max Act: 7.4018. Min Act: -0.1700
Data Index: 4957695 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4018. Min Range: -7.4018
Max Act: 7.2768. Min Act: -0.1700
Data Index: 2642058 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4018. Min Range: -7.4018
Max Act: 7.1205. Min Act: -0.1700
Data Index: 5667337 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4018. Min Range: -7.4018
Max Act: 7.0893. Min Act: -0.1700
Data Index: 2321790 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4018. Min Range: -7.4018
Max Act: 7.0268. Min Act: -0.1700
Data Index: 910179 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4018. Min Range: -7.4018
Max Act: 7.0580. Min Act: -0.1700
Data Index: 2764040 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4018. Min Range: -7.4018
Max Act: 6.9955. Min Act: -0.1700
Data Index: 2133766 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4018. Min Range: -7.4018
Max Act: 6.9643. Min Act: -0.1700
Data Index: 3329729 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4018. Min Range: -7.4018
Max Act: 6.9330. Min Act: -0.1700
Data Index: 3113997 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4018. Min Range: -7.4018
Max Act: 6.9330. Min Act: -0.1700
Data Index: 3115419 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4018. Min Range: -7.4018
Max Act: 6.8705. Min Act: -0.1700
Data Index: 6355751 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4018. Min Range: -7.4018
Max Act: 6.8705. Min Act: -0.1700
Data Index: 149140 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4018. Min Range: -7.4018
Max Act: 6.8705. Min Act: -0.1700
Data Index: 1721638 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4018. Min Range: -7.4018
Max Act: 6.7768. Min Act: -0.1700
Data Index: 1394135 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4018. Min Range: -7.4018
Max Act: 6.7768. Min Act: -0.1700
Data Index: 2836813 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4018. Min Range: -7.4018
Max Act: 6.7455. Min Act: -0.1700
Data Index: 5610786 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4018. Min Range: -7.4018
Max Act: 6.7455. Min Act: -0.1700
Data Index: 2602340 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4018. Min Range: -7.4018
Max Act: 6.7455. Min Act: -0.1700
Data Index: 6142845 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4018. Min Range: -7.4018
Max Act: 6.7143. Min Act: -0.1700
Data Index: 4787678 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4018. Min Range: -7.4018
Max Act: 6.7143. Min Act: -0.1700
Data Index: 2950254 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19