Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3104 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4867. Min Range: -6.4867
Max Act: 6.4867. Min Act: -0.1700
Data Index: 8489361 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4867. Min Range: -6.4867
Max Act: 6.4242. Min Act: -0.1700
Data Index: 3156827 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4867. Min Range: -6.4867
Max Act: 6.2992. Min Act: -0.1700
Data Index: 5626791 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4867. Min Range: -6.4867
Max Act: 6.2680. Min Act: -0.1700
Data Index: 20518 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4867. Min Range: -6.4867
Max Act: 6.2367. Min Act: -0.1700
Data Index: 6760285 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4867. Min Range: -6.4867
Max Act: 6.2367. Min Act: -0.1700
Data Index: 5319376 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4867. Min Range: -6.4867
Max Act: 6.2367. Min Act: -0.1700
Data Index: 3905171 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4867. Min Range: -6.4867
Max Act: 6.2367. Min Act: -0.1700
Data Index: 7920259 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4867. Min Range: -6.4867
Max Act: 6.2367. Min Act: -0.1700
Data Index: 6735091 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4867. Min Range: -6.4867
Max Act: 6.2055. Min Act: -0.1700
Data Index: 7076943 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4867. Min Range: -6.4867
Max Act: 6.1742. Min Act: -0.1700
Data Index: 876893 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4867. Min Range: -6.4867
Max Act: 6.1742. Min Act: -0.1700
Data Index: 7292375 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4867. Min Range: -6.4867
Max Act: 6.1117. Min Act: -0.1700
Data Index: 4111436 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4867. Min Range: -6.4867
Max Act: 6.0805. Min Act: -0.1700
Data Index: 2168503 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4867. Min Range: -6.4867
Max Act: 6.0492. Min Act: -0.1700
Data Index: 782637 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4867. Min Range: -6.4867
Max Act: 6.0180. Min Act: -0.1700
Data Index: 6290562 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4867. Min Range: -6.4867
Max Act: 6.0492. Min Act: -0.1700
Data Index: 2043458 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4867. Min Range: -6.4867
Max Act: 6.0180. Min Act: -0.1700
Data Index: 4872399 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4867. Min Range: -6.4867
Max Act: 6.0180. Min Act: -0.1700
Data Index: 3540325 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4867. Min Range: -6.4867
Max Act: 5.9867. Min Act: -0.1700
Data Index: 4035599 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19