Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3812 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5274. Min Range: -8.5274
Max Act: 8.5274. Min Act: -0.1700
Data Index: 861288 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5274. Min Range: -8.5274
Max Act: 8.5274. Min Act: -0.1700
Data Index: 1652053 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5274. Min Range: -8.5274
Max Act: 8.4649. Min Act: -0.1700
Data Index: 4299405 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5274. Min Range: -8.5274
Max Act: 8.4649. Min Act: -0.1700
Data Index: 1608697 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5274. Min Range: -8.5274
Max Act: 8.2774. Min Act: -0.1700
Data Index: 6408940 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5274. Min Range: -8.5274
Max Act: 8.2774. Min Act: -0.1700
Data Index: 5424539 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5274. Min Range: -8.5274
Max Act: 8.2774. Min Act: -0.1700
Data Index: 4562346 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5274. Min Range: -8.5274
Max Act: 8.2149. Min Act: -0.1700
Data Index: 1274665 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5274. Min Range: -8.5274
Max Act: 8.2149. Min Act: -0.1700
Data Index: 3827945 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5274. Min Range: -8.5274
Max Act: 8.1524. Min Act: -0.1700
Data Index: 7650940 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5274. Min Range: -8.5274
Max Act: 8.1524. Min Act: -0.1700
Data Index: 8230189 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5274. Min Range: -8.5274
Max Act: 8.1524. Min Act: -0.1700
Data Index: 5493743 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5274. Min Range: -8.5274
Max Act: 8.1524. Min Act: -0.1700
Data Index: 8739908 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5274. Min Range: -8.5274
Max Act: 8.0899. Min Act: -0.1700
Data Index: 6009005 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5274. Min Range: -8.5274
Max Act: 8.1524. Min Act: -0.1700
Data Index: 8461694 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5274. Min Range: -8.5274
Max Act: 8.0899. Min Act: -0.1700
Data Index: 6315240 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5274. Min Range: -8.5274
Max Act: 7.9961. Min Act: -0.1700
Data Index: 594897 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5274. Min Range: -8.5274
Max Act: 8.0274. Min Act: -0.1700
Data Index: 6599260 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5274. Min Range: -8.5274
Max Act: 8.0274. Min Act: -0.1700
Data Index: 7637458 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5274. Min Range: -8.5274
Max Act: 8.0274. Min Act: -0.1700
Data Index: 489598 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #19