Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2037 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1637. Min Range: -6.1637
Max Act: 6.1637. Min Act: -0.1700
Data Index: 3131514 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1637. Min Range: -6.1637
Max Act: 6.0387. Min Act: -0.1700
Data Index: 7341410 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1637. Min Range: -6.1637
Max Act: 5.8200. Min Act: -0.1700
Data Index: 5754669 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1637. Min Range: -6.1637
Max Act: 5.8200. Min Act: -0.1700
Data Index: 6660936 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1637. Min Range: -6.1637
Max Act: 5.7887. Min Act: -0.1700
Data Index: 6672426 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1637. Min Range: -6.1637
Max Act: 5.7887. Min Act: -0.1700
Data Index: 5921993 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1637. Min Range: -6.1637
Max Act: 5.7887. Min Act: -0.1700
Data Index: 4413877 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1637. Min Range: -6.1637
Max Act: 5.7262. Min Act: -0.1700
Data Index: 3435725 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1637. Min Range: -6.1637
Max Act: 5.7262. Min Act: -0.1700
Data Index: 1563255 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1637. Min Range: -6.1637
Max Act: 5.6950. Min Act: -0.1700
Data Index: 6797189 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1637. Min Range: -6.1637
Max Act: 5.6950. Min Act: -0.1700
Data Index: 7701648 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1637. Min Range: -6.1637
Max Act: 5.6950. Min Act: -0.1700
Data Index: 2829278 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1637. Min Range: -6.1637
Max Act: 5.6637. Min Act: -0.1700
Data Index: 5971581 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1637. Min Range: -6.1637
Max Act: 5.6637. Min Act: -0.1700
Data Index: 366990 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1637. Min Range: -6.1637
Max Act: 5.6325. Min Act: -0.1700
Data Index: 2868437 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1637. Min Range: -6.1637
Max Act: 5.6950. Min Act: -0.1700
Data Index: 7333859 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1637. Min Range: -6.1637
Max Act: 5.6637. Min Act: -0.1700
Data Index: 4975241 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1637. Min Range: -6.1637
Max Act: 5.6637. Min Act: -0.1700
Data Index: 985986 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1637. Min Range: -6.1637
Max Act: 5.6325. Min Act: -0.1700
Data Index: 2358809 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1637. Min Range: -6.1637
Max Act: 5.6325. Min Act: -0.1700
Data Index: 6604073 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #19