Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3305 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2992. Min Range: -7.2992
Max Act: 7.2992. Min Act: -0.1700
Data Index: 6015449 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2992. Min Range: -7.2992
Max Act: 7.1742. Min Act: -0.1700
Data Index: 889018 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2992. Min Range: -7.2992
Max Act: 7.1742. Min Act: -0.1700
Data Index: 1082015 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2992. Min Range: -7.2992
Max Act: 7.1430. Min Act: -0.1700
Data Index: 7194872 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2992. Min Range: -7.2992
Max Act: 7.0805. Min Act: -0.1700
Data Index: 3105532 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2992. Min Range: -7.2992
Max Act: 7.0180. Min Act: -0.1700
Data Index: 2738082 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2992. Min Range: -7.2992
Max Act: 7.0492. Min Act: -0.1700
Data Index: 5967357 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.9867. Min Act: -0.1700
Data Index: 3611797 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.9867. Min Act: -0.1700
Data Index: 6059935 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.9555. Min Act: -0.1700
Data Index: 6185337 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.8930. Min Act: -0.1700
Data Index: 6285245 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.9555. Min Act: -0.1700
Data Index: 793161 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.9242. Min Act: -0.1700
Data Index: 3325004 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.9555. Min Act: -0.1700
Data Index: 1675539 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.9242. Min Act: -0.1700
Data Index: 4960561 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.9242. Min Act: -0.1700
Data Index: 8460566 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.8930. Min Act: -0.1700
Data Index: 5864973 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.8617. Min Act: -0.1700
Data Index: 3107980 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.8305. Min Act: -0.1700
Data Index: 1763066 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2992. Min Range: -7.2992
Max Act: 6.8305. Min Act: -0.1700
Data Index: 7646129 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #19