Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4943 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.5108. Min Act: -0.1700
Data Index: 6724907 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.4171. Min Act: -0.1700
Data Index: 625718 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.3858. Min Act: -0.1700
Data Index: 319682 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.2296. Min Act: -0.1700
Data Index: 1502489 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.1671. Min Act: -0.1700
Data Index: 4414991 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.1671. Min Act: -0.1700
Data Index: 5421485 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.1358. Min Act: -0.1700
Data Index: 4898729 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.1046. Min Act: -0.1700
Data Index: 7763779 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.1046. Min Act: -0.1700
Data Index: 6035368 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.1046. Min Act: -0.1700
Data Index: 3316479 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.0733. Min Act: -0.1700
Data Index: 3869356 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.0733. Min Act: -0.1700
Data Index: 8427913 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.0733. Min Act: -0.1700
Data Index: 3236169 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.0733. Min Act: -0.1700
Data Index: 6857662 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.0421. Min Act: -0.1700
Data Index: 7121057 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.0421. Min Act: -0.1700
Data Index: 4107993 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.0421. Min Act: -0.1700
Data Index: 5129039 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.0421. Min Act: -0.1700
Data Index: 831303 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.0108. Min Act: -0.1700
Data Index: 8299524 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5108. Min Range: -6.5108
Max Act: 6.0108. Min Act: -0.1700
Data Index: 445923 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19