Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4688 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8960. Min Range: -7.8960
Max Act: 7.8960. Min Act: -0.1700
Data Index: 2907412 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8960. Min Range: -7.8960
Max Act: 7.8335. Min Act: -0.1700
Data Index: 3482059 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8960. Min Range: -7.8960
Max Act: 7.7710. Min Act: -0.1700
Data Index: 8256935 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8960. Min Range: -7.8960
Max Act: 7.6460. Min Act: -0.1700
Data Index: 2574060 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8960. Min Range: -7.8960
Max Act: 7.6772. Min Act: -0.1700
Data Index: 417525 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8960. Min Range: -7.8960
Max Act: 7.6772. Min Act: -0.1700
Data Index: 7634263 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8960. Min Range: -7.8960
Max Act: 7.6460. Min Act: -0.1700
Data Index: 6963563 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8960. Min Range: -7.8960
Max Act: 7.6147. Min Act: -0.1700
Data Index: 4802330 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8960. Min Range: -7.8960
Max Act: 7.5835. Min Act: -0.1700
Data Index: 6854009 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8960. Min Range: -7.8960
Max Act: 7.5522. Min Act: -0.1700
Data Index: 3346886 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8960. Min Range: -7.8960
Max Act: 7.5522. Min Act: -0.1700
Data Index: 6167899 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8960. Min Range: -7.8960
Max Act: 7.5210. Min Act: -0.1700
Data Index: 7781633 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8960. Min Range: -7.8960
Max Act: 7.4897. Min Act: -0.1700
Data Index: 7341833 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8960. Min Range: -7.8960
Max Act: 7.5210. Min Act: -0.1700
Data Index: 2351364 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8960. Min Range: -7.8960
Max Act: 7.5210. Min Act: -0.1700
Data Index: 937370 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8960. Min Range: -7.8960
Max Act: 7.4897. Min Act: -0.1700
Data Index: 8708898 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8960. Min Range: -7.8960
Max Act: 7.4897. Min Act: -0.1700
Data Index: 5537639 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8960. Min Range: -7.8960
Max Act: 7.4272. Min Act: -0.1700
Data Index: 91986 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8960. Min Range: -7.8960
Max Act: 7.4272. Min Act: -0.1700
Data Index: 1751746 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8960. Min Range: -7.8960
Max Act: 7.4272. Min Act: -0.1700
Data Index: 8376279 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #19