Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3159 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8242. Min Range: -6.8242
Max Act: 6.8242. Min Act: -0.1700
Data Index: 1780153 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8242. Min Range: -6.8242
Max Act: 6.6367. Min Act: -0.1700
Data Index: 8573286 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8242. Min Range: -6.8242
Max Act: 6.6055. Min Act: -0.1700
Data Index: 4678699 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8242. Min Range: -6.8242
Max Act: 6.5117. Min Act: -0.1700
Data Index: 6928141 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8242. Min Range: -6.8242
Max Act: 6.4805. Min Act: -0.1700
Data Index: 7593493 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8242. Min Range: -6.8242
Max Act: 6.4180. Min Act: -0.1700
Data Index: 3631839 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8242. Min Range: -6.8242
Max Act: 6.4180. Min Act: -0.1700
Data Index: 4891601 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8242. Min Range: -6.8242
Max Act: 6.4180. Min Act: -0.1700
Data Index: 6243816 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8242. Min Range: -6.8242
Max Act: 6.3867. Min Act: -0.1700
Data Index: 8573285 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8242. Min Range: -6.8242
Max Act: 6.3242. Min Act: -0.1700
Data Index: 2635579 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8242. Min Range: -6.8242
Max Act: 6.3242. Min Act: -0.1700
Data Index: 3611658 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8242. Min Range: -6.8242
Max Act: 6.3242. Min Act: -0.1700
Data Index: 7695770 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8242. Min Range: -6.8242
Max Act: 6.3242. Min Act: -0.1700
Data Index: 2594758 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8242. Min Range: -6.8242
Max Act: 6.3242. Min Act: -0.1700
Data Index: 7278453 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8242. Min Range: -6.8242
Max Act: 6.3242. Min Act: -0.1700
Data Index: 800099 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8242. Min Range: -6.8242
Max Act: 6.2617. Min Act: -0.1700
Data Index: 8652629 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8242. Min Range: -6.8242
Max Act: 6.2930. Min Act: -0.1700
Data Index: 7643286 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8242. Min Range: -6.8242
Max Act: 6.2930. Min Act: -0.1700
Data Index: 1352165 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8242. Min Range: -6.8242
Max Act: 6.2617. Min Act: -0.1700
Data Index: 954926 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8242. Min Range: -6.8242
Max Act: 6.2617. Min Act: -0.1700
Data Index: 2149393 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19