Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3631 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.9440. Min Range: -4.9440
Max Act: 4.9440. Min Act: -0.1700
Data Index: 6902489 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9440. Min Range: -4.9440
Max Act: 4.7877. Min Act: -0.1700
Data Index: 1138375 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9440. Min Range: -4.9440
Max Act: 4.6940. Min Act: -0.1700
Data Index: 1515635 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9440. Min Range: -4.9440
Max Act: 4.6940. Min Act: -0.1700
Data Index: 5366764 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9440. Min Range: -4.9440
Max Act: 4.6627. Min Act: -0.1700
Data Index: 7311062 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9440. Min Range: -4.9440
Max Act: 4.6627. Min Act: -0.1700
Data Index: 120250 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9440. Min Range: -4.9440
Max Act: 4.6315. Min Act: -0.1700
Data Index: 5193469 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9440. Min Range: -4.9440
Max Act: 4.6315. Min Act: -0.1700
Data Index: 4705904 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9440. Min Range: -4.9440
Max Act: 4.6315. Min Act: -0.1700
Data Index: 2141961 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9440. Min Range: -4.9440
Max Act: 4.6627. Min Act: -0.1700
Data Index: 5984581 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9440. Min Range: -4.9440
Max Act: 4.6315. Min Act: -0.1700
Data Index: 6704069 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9440. Min Range: -4.9440
Max Act: 4.6315. Min Act: -0.1700
Data Index: 6519302 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9440. Min Range: -4.9440
Max Act: 4.6315. Min Act: -0.1700
Data Index: 1953631 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9440. Min Range: -4.9440
Max Act: 4.6315. Min Act: -0.1700
Data Index: 1709314 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9440. Min Range: -4.9440
Max Act: 4.6002. Min Act: -0.1700
Data Index: 2528209 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9440. Min Range: -4.9440
Max Act: 4.6002. Min Act: -0.1700
Data Index: 7732980 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9440. Min Range: -4.9440
Max Act: 4.5690. Min Act: -0.1700
Data Index: 2513881 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9440. Min Range: -4.9440
Max Act: 4.5690. Min Act: -0.1700
Data Index: 1166877 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9440. Min Range: -4.9440
Max Act: 4.5690. Min Act: -0.1700
Data Index: 4211364 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9440. Min Range: -4.9440
Max Act: 4.5065. Min Act: -0.1700
Data Index: 3909090 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #19