Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3460 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8004. Min Range: -6.8004
Max Act: 6.8004. Min Act: -0.1700
Data Index: 1708304 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8004. Min Range: -6.8004
Max Act: 6.7692. Min Act: -0.1700
Data Index: 2231008 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8004. Min Range: -6.8004
Max Act: 6.5817. Min Act: -0.1700
Data Index: 1708305 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8004. Min Range: -6.8004
Max Act: 6.4567. Min Act: -0.1700
Data Index: 1979603 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8004. Min Range: -6.8004
Max Act: 6.4254. Min Act: -0.1700
Data Index: 106433 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8004. Min Range: -6.8004
Max Act: 6.3317. Min Act: -0.1700
Data Index: 8805045 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8004. Min Range: -6.8004
Max Act: 6.2692. Min Act: -0.1700
Data Index: 3631225 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8004. Min Range: -6.8004
Max Act: 6.2379. Min Act: -0.1700
Data Index: 8107199 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8004. Min Range: -6.8004
Max Act: 6.2379. Min Act: -0.1700
Data Index: 4198607 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8004. Min Range: -6.8004
Max Act: 6.1129. Min Act: -0.1700
Data Index: 2724897 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8004. Min Range: -6.8004
Max Act: 6.1129. Min Act: -0.1700
Data Index: 1155867 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8004. Min Range: -6.8004
Max Act: 6.0504. Min Act: -0.1700
Data Index: 851355 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8004. Min Range: -6.8004
Max Act: 6.0817. Min Act: -0.1700
Data Index: 7760194 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8004. Min Range: -6.8004
Max Act: 6.0817. Min Act: -0.1700
Data Index: 4908027 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8004. Min Range: -6.8004
Max Act: 6.0817. Min Act: -0.1700
Data Index: 4495809 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8004. Min Range: -6.8004
Max Act: 6.0817. Min Act: -0.1700
Data Index: 7602158 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8004. Min Range: -6.8004
Max Act: 6.1129. Min Act: -0.1700
Data Index: 6970539 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8004. Min Range: -6.8004
Max Act: 6.0504. Min Act: -0.1700
Data Index: 1084418 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8004. Min Range: -6.8004
Max Act: 6.0504. Min Act: -0.1700
Data Index: 3041854 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8004. Min Range: -6.8004
Max Act: 6.0504. Min Act: -0.1700
Data Index: 2506743 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #19