Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1832 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7465. Min Range: -6.7465
Max Act: 6.7465. Min Act: -0.1700
Data Index: 5163754 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7465. Min Range: -6.7465
Max Act: 6.7152. Min Act: -0.1700
Data Index: 2220692 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7465. Min Range: -6.7465
Max Act: 6.6840. Min Act: -0.1700
Data Index: 4457465 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7465. Min Range: -6.7465
Max Act: 6.4652. Min Act: -0.1700
Data Index: 1334683 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7465. Min Range: -6.7465
Max Act: 6.3715. Min Act: -0.1700
Data Index: 8786935 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7465. Min Range: -6.7465
Max Act: 6.3090. Min Act: -0.1700
Data Index: 1147425 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7465. Min Range: -6.7465
Max Act: 6.2777. Min Act: -0.1700
Data Index: 2929418 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7465. Min Range: -6.7465
Max Act: 6.2777. Min Act: -0.1700
Data Index: 3223068 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7465. Min Range: -6.7465
Max Act: 6.2465. Min Act: -0.1700
Data Index: 3282710 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7465. Min Range: -6.7465
Max Act: 6.2465. Min Act: -0.1700
Data Index: 1051953 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7465. Min Range: -6.7465
Max Act: 6.1840. Min Act: -0.1700
Data Index: 8362017 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7465. Min Range: -6.7465
Max Act: 6.1527. Min Act: -0.1700
Data Index: 2386069 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7465. Min Range: -6.7465
Max Act: 6.1215. Min Act: -0.1700
Data Index: 7872652 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7465. Min Range: -6.7465
Max Act: 6.1215. Min Act: -0.1700
Data Index: 6225981 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7465. Min Range: -6.7465
Max Act: 6.1527. Min Act: -0.1700
Data Index: 753798 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7465. Min Range: -6.7465
Max Act: 6.1215. Min Act: -0.1700
Data Index: 5869138 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7465. Min Range: -6.7465
Max Act: 6.1215. Min Act: -0.1700
Data Index: 3827660 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7465. Min Range: -6.7465
Max Act: 6.1215. Min Act: -0.1700
Data Index: 4979073 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7465. Min Range: -6.7465
Max Act: 6.0590. Min Act: -0.1700
Data Index: 4786488 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7465. Min Range: -6.7465
Max Act: 6.0902. Min Act: -0.1700
Data Index: 924184 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19