Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6191 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2401. Min Range: -2.2401
Max Act: 2.2401. Min Act: -0.1700
Data Index: 3449150 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2401. Min Range: -2.2401
Max Act: 2.1904. Min Act: -0.1700
Data Index: 7102048 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2401. Min Range: -2.2401
Max Act: 2.1738. Min Act: -0.1700
Data Index: 6253732 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2401. Min Range: -2.2401
Max Act: 2.1571. Min Act: -0.1700
Data Index: 6324526 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2401. Min Range: -2.2401
Max Act: 2.1237. Min Act: -0.1685
Data Index: 7619633 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2401. Min Range: -2.2401
Max Act: 2.1237. Min Act: -0.1700
Data Index: 8289146 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2401. Min Range: -2.2401
Max Act: 2.1070. Min Act: -0.1700
Data Index: 4891145 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2401. Min Range: -2.2401
Max Act: 2.0903. Min Act: -0.1700
Data Index: 6950969 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2401. Min Range: -2.2401
Max Act: 2.0735. Min Act: -0.1699
Data Index: 2590410 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2401. Min Range: -2.2401
Max Act: 2.0399. Min Act: -0.1700
Data Index: 3387370 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2401. Min Range: -2.2401
Max Act: 2.0399. Min Act: -0.1682
Data Index: 477070 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2401. Min Range: -2.2401
Max Act: 2.0230. Min Act: -0.1700
Data Index: 3643834 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2401. Min Range: -2.2401
Max Act: 2.0230. Min Act: -0.1690
Data Index: 5943520 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2401. Min Range: -2.2401
Max Act: 2.0230. Min Act: -0.1700
Data Index: 4298947 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2401. Min Range: -2.2401
Max Act: 2.0062. Min Act: -0.1700
Data Index: 1657349 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2401. Min Range: -2.2401
Max Act: 1.9892. Min Act: -0.1698
Data Index: 5799739 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2401. Min Range: -2.2401
Max Act: 2.0230. Min Act: -0.1700
Data Index: 4905984 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2401. Min Range: -2.2401
Max Act: 1.9892. Min Act: -0.1700
Data Index: 2749840 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2401. Min Range: -2.2401
Max Act: 1.9892. Min Act: -0.1700
Data Index: 1515024 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2401. Min Range: -2.2401
Max Act: 1.9892. Min Act: -0.1697
Data Index: 4318101 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19