Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1912 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0007. Min Range: -4.0007
Max Act: 4.0007. Min Act: -0.1700
Data Index: 3703520 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0007. Min Range: -4.0007
Max Act: 3.9069. Min Act: -0.1700
Data Index: 4591563 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0007. Min Range: -4.0007
Max Act: 3.9069. Min Act: -0.1700
Data Index: 6150470 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0007. Min Range: -4.0007
Max Act: 3.8287. Min Act: -0.1700
Data Index: 6150460 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0007. Min Range: -4.0007
Max Act: 3.8600. Min Act: -0.1700
Data Index: 2023459 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0007. Min Range: -4.0007
Max Act: 3.7974. Min Act: -0.1700
Data Index: 4756838 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0007. Min Range: -4.0007
Max Act: 3.7818. Min Act: -0.1700
Data Index: 6591001 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0007. Min Range: -4.0007
Max Act: 3.8287. Min Act: -0.1700
Data Index: 6141550 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0007. Min Range: -4.0007
Max Act: 3.7662. Min Act: -0.1700
Data Index: 943588 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0007. Min Range: -4.0007
Max Act: 3.7662. Min Act: -0.1700
Data Index: 3723358 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0007. Min Range: -4.0007
Max Act: 3.7505. Min Act: -0.1700
Data Index: 3109815 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0007. Min Range: -4.0007
Max Act: 3.7505. Min Act: -0.1700
Data Index: 1654128 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0007. Min Range: -4.0007
Max Act: 3.7349. Min Act: -0.1700
Data Index: 7874294 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0007. Min Range: -4.0007
Max Act: 3.7349. Min Act: -0.1700
Data Index: 3979228 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0007. Min Range: -4.0007
Max Act: 3.7192. Min Act: -0.1700
Data Index: 796880 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0007. Min Range: -4.0007
Max Act: 3.7192. Min Act: -0.1700
Data Index: 2903679 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0007. Min Range: -4.0007
Max Act: 3.6880. Min Act: -0.1700
Data Index: 3114010 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0007. Min Range: -4.0007
Max Act: 3.6880. Min Act: -0.1700
Data Index: 4298844 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0007. Min Range: -4.0007
Max Act: 3.7192. Min Act: -0.1700
Data Index: 6142393 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0007. Min Range: -4.0007
Max Act: 3.6723. Min Act: -0.1700
Data Index: 5805016 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19