Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 406 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5209. Min Range: -5.5209
Max Act: 5.5209. Min Act: -0.1700
Data Index: 5869297 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5209. Min Range: -5.5209
Max Act: 5.4897. Min Act: -0.1700
Data Index: 8720888 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5209. Min Range: -5.5209
Max Act: 5.3959. Min Act: -0.1700
Data Index: 2123422 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5209. Min Range: -5.5209
Max Act: 5.3959. Min Act: -0.1700
Data Index: 1688710 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5209. Min Range: -5.5209
Max Act: 5.3334. Min Act: -0.1700
Data Index: 1353605 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5209. Min Range: -5.5209
Max Act: 5.3022. Min Act: -0.1700
Data Index: 5405621 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5209. Min Range: -5.5209
Max Act: 5.3022. Min Act: -0.1700
Data Index: 5432155 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5209. Min Range: -5.5209
Max Act: 5.3334. Min Act: -0.1700
Data Index: 838619 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5209. Min Range: -5.5209
Max Act: 5.3334. Min Act: -0.1700
Data Index: 2243343 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5209. Min Range: -5.5209
Max Act: 5.3022. Min Act: -0.1700
Data Index: 8238426 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5209. Min Range: -5.5209
Max Act: 5.3022. Min Act: -0.1700
Data Index: 3206785 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5209. Min Range: -5.5209
Max Act: 5.2709. Min Act: -0.1700
Data Index: 196922 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5209. Min Range: -5.5209
Max Act: 5.3022. Min Act: -0.1700
Data Index: 3404907 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5209. Min Range: -5.5209
Max Act: 5.2709. Min Act: -0.1700
Data Index: 1970518 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5209. Min Range: -5.5209
Max Act: 5.2709. Min Act: -0.1700
Data Index: 890491 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5209. Min Range: -5.5209
Max Act: 5.2709. Min Act: -0.1700
Data Index: 5277866 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5209. Min Range: -5.5209
Max Act: 5.2709. Min Act: -0.1700
Data Index: 3385999 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5209. Min Range: -5.5209
Max Act: 5.2709. Min Act: -0.1700
Data Index: 6002601 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5209. Min Range: -5.5209
Max Act: 5.2709. Min Act: -0.1700
Data Index: 3287282 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5209. Min Range: -5.5209
Max Act: 5.2397. Min Act: -0.1700
Data Index: 6696010 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19