Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3512 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 20.0215. Min Range: -20.0215
Max Act: 20.0215. Min Act: -0.1700
Data Index: 1618046 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 20.0215. Min Range: -20.0215
Max Act: 19.3965. Min Act: -0.1700
Data Index: 1999767 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 20.0215. Min Range: -20.0215
Max Act: 19.2715. Min Act: -0.1700
Data Index: 6691 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 20.0215. Min Range: -20.0215
Max Act: 19.1465. Min Act: -0.1700
Data Index: 7027364 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 20.0215. Min Range: -20.0215
Max Act: 19.1465. Min Act: -0.1700
Data Index: 6428281 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 20.0215. Min Range: -20.0215
Max Act: 19.0215. Min Act: -0.1700
Data Index: 7531603 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 20.0215. Min Range: -20.0215
Max Act: 18.8965. Min Act: -0.1700
Data Index: 3388710 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 20.0215. Min Range: -20.0215
Max Act: 18.8965. Min Act: -0.1700
Data Index: 5599366 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 20.0215. Min Range: -20.0215
Max Act: 18.8965. Min Act: -0.1700
Data Index: 6064833 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 20.0215. Min Range: -20.0215
Max Act: 18.8965. Min Act: -0.1700
Data Index: 5849984 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 20.0215. Min Range: -20.0215
Max Act: 18.8965. Min Act: -0.1700
Data Index: 7810090 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 20.0215. Min Range: -20.0215
Max Act: 18.7715. Min Act: -0.1700
Data Index: 3383833 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 20.0215. Min Range: -20.0215
Max Act: 18.7715. Min Act: -0.1700
Data Index: 259576 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 20.0215. Min Range: -20.0215
Max Act: 18.6465. Min Act: -0.1700
Data Index: 3473394 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 20.0215. Min Range: -20.0215
Max Act: 18.7715. Min Act: -0.1700
Data Index: 7283842 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 20.0215. Min Range: -20.0215
Max Act: 18.7715. Min Act: -0.1700
Data Index: 7122978 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 20.0215. Min Range: -20.0215
Max Act: 18.6465. Min Act: -0.1700
Data Index: 1019132 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 20.0215. Min Range: -20.0215
Max Act: 18.6465. Min Act: -0.1700
Data Index: 6576815 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 20.0215. Min Range: -20.0215
Max Act: 18.5215. Min Act: -0.1700
Data Index: 5849682 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 20.0215. Min Range: -20.0215
Max Act: 18.5215. Min Act: -0.1700
Data Index: 5141452 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19