Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4297 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6060. Min Range: -6.6060
Max Act: 6.6060. Min Act: -0.1700
Data Index: 7871287 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6060. Min Range: -6.6060
Max Act: 6.5435. Min Act: -0.1700
Data Index: 5836265 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6060. Min Range: -6.6060
Max Act: 6.4497. Min Act: -0.1700
Data Index: 4458998 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6060. Min Range: -6.6060
Max Act: 6.4810. Min Act: -0.1700
Data Index: 4012188 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6060. Min Range: -6.6060
Max Act: 6.3872. Min Act: -0.1700
Data Index: 70181 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6060. Min Range: -6.6060
Max Act: 6.3247. Min Act: -0.1700
Data Index: 5920379 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6060. Min Range: -6.6060
Max Act: 6.3247. Min Act: -0.1700
Data Index: 2143728 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6060. Min Range: -6.6060
Max Act: 6.2935. Min Act: -0.1700
Data Index: 5345535 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6060. Min Range: -6.6060
Max Act: 6.2935. Min Act: -0.1700
Data Index: 5399153 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6060. Min Range: -6.6060
Max Act: 6.2935. Min Act: -0.1700
Data Index: 3327367 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6060. Min Range: -6.6060
Max Act: 6.1997. Min Act: -0.1700
Data Index: 1208538 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6060. Min Range: -6.6060
Max Act: 6.1997. Min Act: -0.1700
Data Index: 21467 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6060. Min Range: -6.6060
Max Act: 6.1997. Min Act: -0.1700
Data Index: 5623033 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6060. Min Range: -6.6060
Max Act: 6.1997. Min Act: -0.1700
Data Index: 680359 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6060. Min Range: -6.6060
Max Act: 6.1997. Min Act: -0.1700
Data Index: 4024861 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6060. Min Range: -6.6060
Max Act: 6.1685. Min Act: -0.1700
Data Index: 8567524 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6060. Min Range: -6.6060
Max Act: 6.1685. Min Act: -0.1700
Data Index: 1821169 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6060. Min Range: -6.6060
Max Act: 6.1372. Min Act: -0.1700
Data Index: 1386765 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6060. Min Range: -6.6060
Max Act: 6.1372. Min Act: -0.1700
Data Index: 3785780 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6060. Min Range: -6.6060
Max Act: 6.1060. Min Act: -0.1700
Data Index: 3467560 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #19