Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2119 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.2413. Min Range: -1.2413
Max Act: 1.2413. Min Act: -0.1699
Data Index: 5566926 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2413. Min Range: -1.2413
Max Act: 1.1885. Min Act: -0.1684
Data Index: 7258509 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2413. Min Range: -1.2413
Max Act: 1.1885. Min Act: -0.1700
Data Index: 2139042 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2413. Min Range: -1.2413
Max Act: 1.1533. Min Act: -0.1700
Data Index: 8592224 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2413. Min Range: -1.2413
Max Act: 1.1709. Min Act: -0.1700
Data Index: 235074 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2413. Min Range: -1.2413
Max Act: 1.1533. Min Act: -0.1652
Data Index: 746987 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2413. Min Range: -1.2413
Max Act: 1.1357. Min Act: -0.1700
Data Index: 5845400 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2413. Min Range: -1.2413
Max Act: 1.1357. Min Act: -0.1700
Data Index: 5845402 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2413. Min Range: -1.2413
Max Act: 1.1357. Min Act: -0.1700
Data Index: 378318 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2413. Min Range: -1.2413
Max Act: 1.1007. Min Act: -0.1698
Data Index: 6301244 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2413. Min Range: -1.2413
Max Act: 1.1182. Min Act: -0.1700
Data Index: 8107246 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2413. Min Range: -1.2413
Max Act: 1.1007. Min Act: -0.1700
Data Index: 1898247 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2413. Min Range: -1.2413
Max Act: 1.1007. Min Act: -0.1700
Data Index: 831252 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2413. Min Range: -1.2413
Max Act: 1.1357. Min Act: -0.1700
Data Index: 4257100 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2413. Min Range: -1.2413
Max Act: 1.1182. Min Act: -0.1699
Data Index: 5956045 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2413. Min Range: -1.2413
Max Act: 1.1007. Min Act: -0.1699
Data Index: 7037961 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2413. Min Range: -1.2413
Max Act: 1.0919. Min Act: -0.1694
Data Index: 7819039 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2413. Min Range: -1.2413
Max Act: 1.0832. Min Act: -0.1700
Data Index: 733700 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2413. Min Range: -1.2413
Max Act: 1.0657. Min Act: -0.1700
Data Index: 66902 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2413. Min Range: -1.2413
Max Act: 1.0657. Min Act: -0.1700
Data Index: 7443016 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #19