Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1005 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 13.2144. Min Range: -13.2144
Max Act: 13.2144. Min Act: -0.1700
Data Index: 1170250 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 13.2144. Min Range: -13.2144
Max Act: 13.1519. Min Act: -0.1700
Data Index: 8711773 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 13.2144. Min Range: -13.2144
Max Act: 13.0269. Min Act: -0.1700
Data Index: 4955046 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 13.2144. Min Range: -13.2144
Max Act: 12.9644. Min Act: -0.1700
Data Index: 1121638 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 13.2144. Min Range: -13.2144
Max Act: 12.9644. Min Act: -0.1700
Data Index: 3551686 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 13.2144. Min Range: -13.2144
Max Act: 12.9019. Min Act: -0.1700
Data Index: 4509010 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 13.2144. Min Range: -13.2144
Max Act: 12.8394. Min Act: -0.1700
Data Index: 2744856 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 13.2144. Min Range: -13.2144
Max Act: 12.7769. Min Act: -0.1700
Data Index: 351688 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 13.2144. Min Range: -13.2144
Max Act: 12.7769. Min Act: -0.1700
Data Index: 595719 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 13.2144. Min Range: -13.2144
Max Act: 12.7769. Min Act: -0.1700
Data Index: 2584193 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 13.2144. Min Range: -13.2144
Max Act: 12.7144. Min Act: -0.1700
Data Index: 3926490 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 13.2144. Min Range: -13.2144
Max Act: 12.7144. Min Act: -0.1700
Data Index: 3280297 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 13.2144. Min Range: -13.2144
Max Act: 12.7144. Min Act: -0.1700
Data Index: 8599816 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 13.2144. Min Range: -13.2144
Max Act: 12.6519. Min Act: -0.1700
Data Index: 790151 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 13.2144. Min Range: -13.2144
Max Act: 12.6519. Min Act: -0.1700
Data Index: 1506684 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 13.2144. Min Range: -13.2144
Max Act: 12.6519. Min Act: -0.1700
Data Index: 2089350 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 13.2144. Min Range: -13.2144
Max Act: 12.6519. Min Act: -0.1700
Data Index: 2567955 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 13.2144. Min Range: -13.2144
Max Act: 12.6519. Min Act: -0.1700
Data Index: 3945392 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 13.2144. Min Range: -13.2144
Max Act: 12.6519. Min Act: -0.1700
Data Index: 2479178 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 13.2144. Min Range: -13.2144
Max Act: 12.6519. Min Act: -0.1700
Data Index: 6222742 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #19