Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 857 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5664. Min Range: -8.5664
Max Act: 8.5664. Min Act: -0.1700
Data Index: 2898906 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5664. Min Range: -8.5664
Max Act: 8.5664. Min Act: -0.1700
Data Index: 7666196 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5664. Min Range: -8.5664
Max Act: 8.5039. Min Act: -0.1700
Data Index: 3564306 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5664. Min Range: -8.5664
Max Act: 8.5039. Min Act: -0.1700
Data Index: 4525316 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5664. Min Range: -8.5664
Max Act: 8.4414. Min Act: -0.1700
Data Index: 8225789 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5664. Min Range: -8.5664
Max Act: 8.3789. Min Act: -0.1700
Data Index: 2666602 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5664. Min Range: -8.5664
Max Act: 8.3789. Min Act: -0.1700
Data Index: 1231645 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5664. Min Range: -8.5664
Max Act: 8.3164. Min Act: -0.1700
Data Index: 416866 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5664. Min Range: -8.5664
Max Act: 8.2539. Min Act: -0.1700
Data Index: 5372254 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5664. Min Range: -8.5664
Max Act: 8.2539. Min Act: -0.1700
Data Index: 2320924 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5664. Min Range: -8.5664
Max Act: 8.1914. Min Act: -0.1700
Data Index: 5999773 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5664. Min Range: -8.5664
Max Act: 8.1914. Min Act: -0.1700
Data Index: 1352768 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5664. Min Range: -8.5664
Max Act: 8.1289. Min Act: -0.1700
Data Index: 1660464 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5664. Min Range: -8.5664
Max Act: 8.1289. Min Act: -0.1700
Data Index: 1138317 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5664. Min Range: -8.5664
Max Act: 8.1289. Min Act: -0.1700
Data Index: 3918829 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5664. Min Range: -8.5664
Max Act: 8.0664. Min Act: -0.1700
Data Index: 5683845 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5664. Min Range: -8.5664
Max Act: 8.0664. Min Act: -0.1700
Data Index: 5050364 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5664. Min Range: -8.5664
Max Act: 8.0664. Min Act: -0.1700
Data Index: 736664 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5664. Min Range: -8.5664
Max Act: 8.0039. Min Act: -0.1700
Data Index: 8048500 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5664. Min Range: -8.5664
Max Act: 8.0664. Min Act: -0.1700
Data Index: 1509715 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19