Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3319 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2034. Min Range: -8.2034
Max Act: 8.2034. Min Act: -0.1700
Data Index: 4272387 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2034. Min Range: -8.2034
Max Act: 8.2034. Min Act: -0.1700
Data Index: 1566718 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2034. Min Range: -8.2034
Max Act: 7.8909. Min Act: -0.1700
Data Index: 987413 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2034. Min Range: -8.2034
Max Act: 7.8909. Min Act: -0.1700
Data Index: 4231572 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2034. Min Range: -8.2034
Max Act: 7.8909. Min Act: -0.1700
Data Index: 8686491 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2034. Min Range: -8.2034
Max Act: 7.8597. Min Act: -0.1700
Data Index: 8103782 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2034. Min Range: -8.2034
Max Act: 7.7659. Min Act: -0.1700
Data Index: 8398605 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2034. Min Range: -8.2034
Max Act: 7.7972. Min Act: -0.1700
Data Index: 8609190 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2034. Min Range: -8.2034
Max Act: 7.7347. Min Act: -0.1700
Data Index: 3861388 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2034. Min Range: -8.2034
Max Act: 7.7034. Min Act: -0.1700
Data Index: 477544 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2034. Min Range: -8.2034
Max Act: 7.6722. Min Act: -0.1700
Data Index: 8619329 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2034. Min Range: -8.2034
Max Act: 7.6722. Min Act: -0.1700
Data Index: 4109635 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2034. Min Range: -8.2034
Max Act: 7.6097. Min Act: -0.1700
Data Index: 6223898 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2034. Min Range: -8.2034
Max Act: 7.6722. Min Act: -0.1700
Data Index: 5574664 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2034. Min Range: -8.2034
Max Act: 7.6097. Min Act: -0.1700
Data Index: 3392264 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2034. Min Range: -8.2034
Max Act: 7.6097. Min Act: -0.1700
Data Index: 992381 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2034. Min Range: -8.2034
Max Act: 7.5784. Min Act: -0.1700
Data Index: 8556825 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2034. Min Range: -8.2034
Max Act: 7.5472. Min Act: -0.1700
Data Index: 8520430 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2034. Min Range: -8.2034
Max Act: 7.5784. Min Act: -0.1700
Data Index: 186188 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2034. Min Range: -8.2034
Max Act: 7.5784. Min Act: -0.1700
Data Index: 7986123 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19