Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1066 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6289. Min Range: -8.6289
Max Act: 8.6289. Min Act: -0.1700
Data Index: 5392080 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6289. Min Range: -8.6289
Max Act: 8.3789. Min Act: -0.1700
Data Index: 5114750 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6289. Min Range: -8.6289
Max Act: 8.0664. Min Act: -0.1700
Data Index: 7941945 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6289. Min Range: -8.6289
Max Act: 7.9102. Min Act: -0.1700
Data Index: 8694033 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6289. Min Range: -8.6289
Max Act: 7.8477. Min Act: -0.1700
Data Index: 5833234 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6289. Min Range: -8.6289
Max Act: 7.8789. Min Act: -0.1700
Data Index: 7836806 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6289. Min Range: -8.6289
Max Act: 7.8477. Min Act: -0.1700
Data Index: 835617 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6289. Min Range: -8.6289
Max Act: 7.8164. Min Act: -0.1700
Data Index: 3226899 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6289. Min Range: -8.6289
Max Act: 7.8164. Min Act: -0.1700
Data Index: 2661220 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6289. Min Range: -8.6289
Max Act: 7.7852. Min Act: -0.1700
Data Index: 1338792 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6289. Min Range: -8.6289
Max Act: 7.7539. Min Act: -0.1700
Data Index: 3746675 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6289. Min Range: -8.6289
Max Act: 7.7852. Min Act: -0.1700
Data Index: 7465408 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6289. Min Range: -8.6289
Max Act: 7.8164. Min Act: -0.1700
Data Index: 4013 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6289. Min Range: -8.6289
Max Act: 7.7227. Min Act: -0.1700
Data Index: 6970710 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6289. Min Range: -8.6289
Max Act: 7.6914. Min Act: -0.1700
Data Index: 8395608 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6289. Min Range: -8.6289
Max Act: 7.6602. Min Act: -0.1700
Data Index: 8278591 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6289. Min Range: -8.6289
Max Act: 7.5977. Min Act: -0.1700
Data Index: 8731144 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6289. Min Range: -8.6289
Max Act: 7.6289. Min Act: -0.1700
Data Index: 8039981 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6289. Min Range: -8.6289
Max Act: 7.5977. Min Act: -0.1700
Data Index: 1172280 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6289. Min Range: -8.6289
Max Act: 7.5664. Min Act: -0.1700
Data Index: 3579113 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #19