Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1165 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 9.5448. Min Range: -9.5448
Max Act: 9.5448. Min Act: -0.1700
Data Index: 3922354 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5448. Min Range: -9.5448
Max Act: 9.3573. Min Act: -0.1700
Data Index: 4099661 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5448. Min Range: -9.5448
Max Act: 9.2948. Min Act: -0.1700
Data Index: 4215903 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5448. Min Range: -9.5448
Max Act: 9.1698. Min Act: -0.1700
Data Index: 3697486 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5448. Min Range: -9.5448
Max Act: 9.1073. Min Act: -0.1700
Data Index: 6394826 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5448. Min Range: -9.5448
Max Act: 9.1073. Min Act: -0.1700
Data Index: 8193271 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5448. Min Range: -9.5448
Max Act: 9.1073. Min Act: -0.1700
Data Index: 8130183 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5448. Min Range: -9.5448
Max Act: 9.0448. Min Act: -0.1700
Data Index: 7223663 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5448. Min Range: -9.5448
Max Act: 8.9823. Min Act: -0.1700
Data Index: 2509458 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5448. Min Range: -9.5448
Max Act: 9.0448. Min Act: -0.1700
Data Index: 6334946 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5448. Min Range: -9.5448
Max Act: 9.0448. Min Act: -0.1700
Data Index: 4780854 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5448. Min Range: -9.5448
Max Act: 9.0448. Min Act: -0.1700
Data Index: 1619336 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5448. Min Range: -9.5448
Max Act: 8.9823. Min Act: -0.1700
Data Index: 1867943 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5448. Min Range: -9.5448
Max Act: 8.9198. Min Act: -0.1700
Data Index: 641800 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5448. Min Range: -9.5448
Max Act: 9.0448. Min Act: -0.1700
Data Index: 8453508 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5448. Min Range: -9.5448
Max Act: 8.9823. Min Act: -0.1700
Data Index: 4707449 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5448. Min Range: -9.5448
Max Act: 8.9823. Min Act: -0.1700
Data Index: 3581057 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5448. Min Range: -9.5448
Max Act: 8.9823. Min Act: -0.1700
Data Index: 7389388 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5448. Min Range: -9.5448
Max Act: 8.9198. Min Act: -0.1700
Data Index: 133063 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5448. Min Range: -9.5448
Max Act: 8.8573. Min Act: -0.1700
Data Index: 6759158 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19