Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1733 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0914. Min Range: -7.0914
Max Act: 7.0914. Min Act: -0.1700
Data Index: 5114821 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0914. Min Range: -7.0914
Max Act: 7.0602. Min Act: -0.1700
Data Index: 3438123 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0914. Min Range: -7.0914
Max Act: 6.9352. Min Act: -0.1700
Data Index: 6584426 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0914. Min Range: -7.0914
Max Act: 6.8414. Min Act: -0.1700
Data Index: 1455866 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0914. Min Range: -7.0914
Max Act: 6.8102. Min Act: -0.1700
Data Index: 2552013 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0914. Min Range: -7.0914
Max Act: 6.8414. Min Act: -0.1700
Data Index: 6523202 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0914. Min Range: -7.0914
Max Act: 6.6852. Min Act: -0.1700
Data Index: 5222721 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0914. Min Range: -7.0914
Max Act: 6.6227. Min Act: -0.1700
Data Index: 2284632 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0914. Min Range: -7.0914
Max Act: 6.5914. Min Act: -0.1700
Data Index: 3688553 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0914. Min Range: -7.0914
Max Act: 6.5289. Min Act: -0.1700
Data Index: 3925342 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0914. Min Range: -7.0914
Max Act: 6.5602. Min Act: -0.1700
Data Index: 1872678 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0914. Min Range: -7.0914
Max Act: 6.5602. Min Act: -0.1700
Data Index: 6732869 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0914. Min Range: -7.0914
Max Act: 6.5602. Min Act: -0.1700
Data Index: 6523199 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0914. Min Range: -7.0914
Max Act: 6.5289. Min Act: -0.1700
Data Index: 7739333 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0914. Min Range: -7.0914
Max Act: 6.5289. Min Act: -0.1700
Data Index: 7165563 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0914. Min Range: -7.0914
Max Act: 6.4977. Min Act: -0.1700
Data Index: 8034701 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0914. Min Range: -7.0914
Max Act: 6.4977. Min Act: -0.1700
Data Index: 7211448 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0914. Min Range: -7.0914
Max Act: 6.4977. Min Act: -0.1700
Data Index: 7589795 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0914. Min Range: -7.0914
Max Act: 6.4352. Min Act: -0.1700
Data Index: 7204785 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0914. Min Range: -7.0914
Max Act: 6.4664. Min Act: -0.1700
Data Index: 2599325 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #19