Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4002 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.4108. Min Range: -8.4108
Max Act: 8.4108. Min Act: -0.1700
Data Index: 788333 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4108. Min Range: -8.4108
Max Act: 8.0045. Min Act: -0.1700
Data Index: 2721853 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4108. Min Range: -8.4108
Max Act: 8.0983. Min Act: -0.1700
Data Index: 219880 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4108. Min Range: -8.4108
Max Act: 8.0670. Min Act: -0.1700
Data Index: 2083817 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4108. Min Range: -8.4108
Max Act: 8.0045. Min Act: -0.1700
Data Index: 6318010 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4108. Min Range: -8.4108
Max Act: 7.9733. Min Act: -0.1700
Data Index: 7755446 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4108. Min Range: -8.4108
Max Act: 7.7545. Min Act: -0.1700
Data Index: 7333594 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4108. Min Range: -8.4108
Max Act: 7.7233. Min Act: -0.1700
Data Index: 426255 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4108. Min Range: -8.4108
Max Act: 7.6295. Min Act: -0.1700
Data Index: 7122141 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4108. Min Range: -8.4108
Max Act: 7.6608. Min Act: -0.1700
Data Index: 8529794 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4108. Min Range: -8.4108
Max Act: 7.3795. Min Act: -0.1694
Data Index: 5924661 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4108. Min Range: -8.4108
Max Act: 7.3483. Min Act: -0.1700
Data Index: 1940002 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4108. Min Range: -8.4108
Max Act: 7.4108. Min Act: -0.1700
Data Index: 1102255 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4108. Min Range: -8.4108
Max Act: 7.3170. Min Act: -0.1696
Data Index: 2238863 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4108. Min Range: -8.4108
Max Act: 7.3170. Min Act: -0.1700
Data Index: 1177690 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4108. Min Range: -8.4108
Max Act: 7.3170. Min Act: -0.1700
Data Index: 4482972 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4108. Min Range: -8.4108
Max Act: 7.1920. Min Act: -0.1700
Data Index: 7776426 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4108. Min Range: -8.4108
Max Act: 7.2233. Min Act: -0.1700
Data Index: 1950815 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4108. Min Range: -8.4108
Max Act: 7.2545. Min Act: -0.1700
Data Index: 1332286 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4108. Min Range: -8.4108
Max Act: 7.2545. Min Act: -0.1700
Data Index: 5891926 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19