Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6254 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0666. Min Range: -7.0666
Max Act: 7.0666. Min Act: -0.1700
Data Index: 1099951 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0666. Min Range: -7.0666
Max Act: 7.0041. Min Act: -0.1700
Data Index: 3823321 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0666. Min Range: -7.0666
Max Act: 7.0041. Min Act: -0.1700
Data Index: 488079 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0666. Min Range: -7.0666
Max Act: 6.9728. Min Act: -0.1700
Data Index: 3274911 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0666. Min Range: -7.0666
Max Act: 6.9416. Min Act: -0.1700
Data Index: 7401496 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0666. Min Range: -7.0666
Max Act: 6.8791. Min Act: -0.1700
Data Index: 4363729 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0666. Min Range: -7.0666
Max Act: 6.8478. Min Act: -0.1700
Data Index: 2892908 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0666. Min Range: -7.0666
Max Act: 6.8478. Min Act: -0.1700
Data Index: 5544857 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0666. Min Range: -7.0666
Max Act: 6.8166. Min Act: -0.1700
Data Index: 6955338 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0666. Min Range: -7.0666
Max Act: 6.8166. Min Act: -0.1700
Data Index: 7088659 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0666. Min Range: -7.0666
Max Act: 6.8166. Min Act: -0.1700
Data Index: 7231652 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0666. Min Range: -7.0666
Max Act: 6.7228. Min Act: -0.1700
Data Index: 7433865 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0666. Min Range: -7.0666
Max Act: 6.7228. Min Act: -0.1700
Data Index: 4056469 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0666. Min Range: -7.0666
Max Act: 6.6916. Min Act: -0.1700
Data Index: 4900251 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0666. Min Range: -7.0666
Max Act: 6.6603. Min Act: -0.1700
Data Index: 1111106 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0666. Min Range: -7.0666
Max Act: 6.6603. Min Act: -0.1700
Data Index: 4374654 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0666. Min Range: -7.0666
Max Act: 6.6916. Min Act: -0.1700
Data Index: 1566546 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0666. Min Range: -7.0666
Max Act: 6.6291. Min Act: -0.1700
Data Index: 7077478 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0666. Min Range: -7.0666
Max Act: 6.6291. Min Act: -0.1700
Data Index: 4490331 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0666. Min Range: -7.0666
Max Act: 6.6291. Min Act: -0.1700
Data Index: 1423283 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19