Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3587 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.8347. Min Act: -0.1700
Data Index: 7806236 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.8034. Min Act: -0.1700
Data Index: 4052527 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.7722. Min Act: -0.1700
Data Index: 3874607 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.7097. Min Act: -0.1700
Data Index: 4021083 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.6784. Min Act: -0.1700
Data Index: 4979443 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.6159. Min Act: -0.1700
Data Index: 1986678 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.5847. Min Act: -0.1700
Data Index: 2855663 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.5847. Min Act: -0.1700
Data Index: 3192964 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.5847. Min Act: -0.1700
Data Index: 6982164 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.5534. Min Act: -0.1700
Data Index: 3001251 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.5534. Min Act: -0.1700
Data Index: 874391 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.5222. Min Act: -0.1700
Data Index: 3471462 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.5222. Min Act: -0.1700
Data Index: 5350247 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.5534. Min Act: -0.1700
Data Index: 810980 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.4909. Min Act: -0.1700
Data Index: 8525376 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.4909. Min Act: -0.1700
Data Index: 2910032 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.4909. Min Act: -0.1700
Data Index: 6361436 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.4597. Min Act: -0.1700
Data Index: 3369398 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.4597. Min Act: -0.1700
Data Index: 870926 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8347. Min Range: -5.8347
Max Act: 5.4597. Min Act: -0.1700
Data Index: 6262610 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19