Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3829 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2006. Min Range: -7.2006
Max Act: 7.2006. Min Act: -0.1700
Data Index: 8198206 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2006. Min Range: -7.2006
Max Act: 7.1381. Min Act: -0.1700
Data Index: 6473491 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2006. Min Range: -7.2006
Max Act: 6.9193. Min Act: -0.1700
Data Index: 3228783 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2006. Min Range: -7.2006
Max Act: 6.8568. Min Act: -0.1700
Data Index: 1356909 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2006. Min Range: -7.2006
Max Act: 6.8568. Min Act: -0.1700
Data Index: 6548573 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2006. Min Range: -7.2006
Max Act: 6.8568. Min Act: -0.1700
Data Index: 2299208 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2006. Min Range: -7.2006
Max Act: 6.8568. Min Act: -0.1700
Data Index: 2651225 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2006. Min Range: -7.2006
Max Act: 6.7631. Min Act: -0.1700
Data Index: 1611135 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2006. Min Range: -7.2006
Max Act: 6.7631. Min Act: -0.1700
Data Index: 5289340 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2006. Min Range: -7.2006
Max Act: 6.7318. Min Act: -0.1700
Data Index: 7391319 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2006. Min Range: -7.2006
Max Act: 6.7318. Min Act: -0.1700
Data Index: 456847 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2006. Min Range: -7.2006
Max Act: 6.7318. Min Act: -0.1700
Data Index: 5868724 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2006. Min Range: -7.2006
Max Act: 6.7631. Min Act: -0.1700
Data Index: 530081 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2006. Min Range: -7.2006
Max Act: 6.7318. Min Act: -0.1700
Data Index: 5979128 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2006. Min Range: -7.2006
Max Act: 6.7006. Min Act: -0.1700
Data Index: 5250757 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2006. Min Range: -7.2006
Max Act: 6.7006. Min Act: -0.1700
Data Index: 1780686 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2006. Min Range: -7.2006
Max Act: 6.7318. Min Act: -0.1700
Data Index: 7693410 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2006. Min Range: -7.2006
Max Act: 6.6381. Min Act: -0.1700
Data Index: 2785886 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2006. Min Range: -7.2006
Max Act: 6.6381. Min Act: -0.1700
Data Index: 4315529 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2006. Min Range: -7.2006
Max Act: 6.6381. Min Act: -0.1700
Data Index: 788784 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #19