Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2536 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5123. Min Range: -6.5123
Max Act: 6.5123. Min Act: -0.1700
Data Index: 7707274 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5123. Min Range: -6.5123
Max Act: 6.4498. Min Act: -0.1700
Data Index: 712698 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5123. Min Range: -6.5123
Max Act: 6.3248. Min Act: -0.1700
Data Index: 5583565 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5123. Min Range: -6.5123
Max Act: 6.3248. Min Act: -0.1700
Data Index: 8724877 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5123. Min Range: -6.5123
Max Act: 6.3248. Min Act: -0.1700
Data Index: 688765 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5123. Min Range: -6.5123
Max Act: 6.2623. Min Act: -0.1700
Data Index: 4932905 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5123. Min Range: -6.5123
Max Act: 6.2310. Min Act: -0.1700
Data Index: 579093 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5123. Min Range: -6.5123
Max Act: 6.1998. Min Act: -0.1700
Data Index: 6594216 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5123. Min Range: -6.5123
Max Act: 6.1998. Min Act: -0.1700
Data Index: 4287820 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5123. Min Range: -6.5123
Max Act: 6.1685. Min Act: -0.1700
Data Index: 1509255 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5123. Min Range: -6.5123
Max Act: 6.1373. Min Act: -0.1700
Data Index: 6797772 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5123. Min Range: -6.5123
Max Act: 6.1685. Min Act: -0.1700
Data Index: 1760913 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5123. Min Range: -6.5123
Max Act: 6.1373. Min Act: -0.1700
Data Index: 3794355 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5123. Min Range: -6.5123
Max Act: 6.1373. Min Act: -0.1700
Data Index: 3320799 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5123. Min Range: -6.5123
Max Act: 6.1373. Min Act: -0.1700
Data Index: 799993 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5123. Min Range: -6.5123
Max Act: 6.1060. Min Act: -0.1700
Data Index: 8238093 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5123. Min Range: -6.5123
Max Act: 6.1060. Min Act: -0.1700
Data Index: 5399554 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5123. Min Range: -6.5123
Max Act: 6.0435. Min Act: -0.1700
Data Index: 1222558 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5123. Min Range: -6.5123
Max Act: 6.0435. Min Act: -0.1700
Data Index: 8417404 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5123. Min Range: -6.5123
Max Act: 6.0435. Min Act: -0.1700
Data Index: 5118428 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #19