Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3578 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9274. Min Range: -4.9274
Max Act: 4.9274. Min Act: -0.1700
Data Index: 4031414 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9274. Min Range: -4.9274
Max Act: 4.8961. Min Act: -0.1700
Data Index: 928052 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9274. Min Range: -4.9274
Max Act: 4.8649. Min Act: -0.1700
Data Index: 5395807 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9274. Min Range: -4.9274
Max Act: 4.7711. Min Act: -0.1700
Data Index: 6744581 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9274. Min Range: -4.9274
Max Act: 4.7711. Min Act: -0.1700
Data Index: 5605068 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9274. Min Range: -4.9274
Max Act: 4.7711. Min Act: -0.1700
Data Index: 5220233 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9274. Min Range: -4.9274
Max Act: 4.7086. Min Act: -0.1700
Data Index: 3159895 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9274. Min Range: -4.9274
Max Act: 4.6461. Min Act: -0.1700
Data Index: 4037477 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9274. Min Range: -4.9274
Max Act: 4.6774. Min Act: -0.1700
Data Index: 8400942 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9274. Min Range: -4.9274
Max Act: 4.6461. Min Act: -0.1700
Data Index: 5332428 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9274. Min Range: -4.9274
Max Act: 4.6774. Min Act: -0.1700
Data Index: 4323165 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9274. Min Range: -4.9274
Max Act: 4.6774. Min Act: -0.1700
Data Index: 4586753 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9274. Min Range: -4.9274
Max Act: 4.6774. Min Act: -0.1700
Data Index: 5211045 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9274. Min Range: -4.9274
Max Act: 4.6461. Min Act: -0.1700
Data Index: 1461179 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9274. Min Range: -4.9274
Max Act: 4.6774. Min Act: -0.1700
Data Index: 4315546 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9274. Min Range: -4.9274
Max Act: 4.6774. Min Act: -0.1700
Data Index: 2754287 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9274. Min Range: -4.9274
Max Act: 4.6461. Min Act: -0.1700
Data Index: 6227765 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9274. Min Range: -4.9274
Max Act: 4.6461. Min Act: -0.1700
Data Index: 973952 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9274. Min Range: -4.9274
Max Act: 4.6461. Min Act: -0.1700
Data Index: 5465637 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9274. Min Range: -4.9274
Max Act: 4.6149. Min Act: -0.1700
Data Index: 4789841 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19