Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5065 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3914. Min Range: -6.3914
Max Act: 6.3914. Min Act: -0.1700
Data Index: 1466676 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3914. Min Range: -6.3914
Max Act: 6.2977. Min Act: -0.1700
Data Index: 8553273 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3914. Min Range: -6.3914
Max Act: 6.1727. Min Act: -0.1700
Data Index: 2248962 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3914. Min Range: -6.3914
Max Act: 6.0477. Min Act: -0.1700
Data Index: 7983947 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3914. Min Range: -6.3914
Max Act: 6.0477. Min Act: -0.1700
Data Index: 4536151 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3914. Min Range: -6.3914
Max Act: 6.0164. Min Act: -0.1700
Data Index: 4169327 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3914. Min Range: -6.3914
Max Act: 5.9852. Min Act: -0.1700
Data Index: 2071249 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3914. Min Range: -6.3914
Max Act: 5.9852. Min Act: -0.1700
Data Index: 5564640 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3914. Min Range: -6.3914
Max Act: 5.9539. Min Act: -0.1700
Data Index: 3078942 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3914. Min Range: -6.3914
Max Act: 5.9227. Min Act: -0.1700
Data Index: 6124718 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3914. Min Range: -6.3914
Max Act: 5.9227. Min Act: -0.1700
Data Index: 801232 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3914. Min Range: -6.3914
Max Act: 5.9227. Min Act: -0.1700
Data Index: 1240830 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3914. Min Range: -6.3914
Max Act: 5.8914. Min Act: -0.1700
Data Index: 8241456 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3914. Min Range: -6.3914
Max Act: 5.8914. Min Act: -0.1700
Data Index: 2625307 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3914. Min Range: -6.3914
Max Act: 5.8914. Min Act: -0.1700
Data Index: 3600049 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3914. Min Range: -6.3914
Max Act: 5.8602. Min Act: -0.1700
Data Index: 1855220 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3914. Min Range: -6.3914
Max Act: 5.8602. Min Act: -0.1700
Data Index: 961093 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3914. Min Range: -6.3914
Max Act: 5.8289. Min Act: -0.1700
Data Index: 4157342 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3914. Min Range: -6.3914
Max Act: 5.8602. Min Act: -0.1700
Data Index: 4114963 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3914. Min Range: -6.3914
Max Act: 5.8914. Min Act: -0.1700
Data Index: 3429608 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #19