Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 926 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.5220. Min Range: -14.5220
Max Act: 14.5220. Min Act: -0.1700
Data Index: 2018982 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.5220. Min Range: -14.5220
Max Act: 14.3970. Min Act: -0.1700
Data Index: 8717850 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.5220. Min Range: -14.5220
Max Act: 14.3345. Min Act: -0.1700
Data Index: 4550846 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.5220. Min Range: -14.5220
Max Act: 14.2720. Min Act: -0.1700
Data Index: 4280948 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.5220. Min Range: -14.5220
Max Act: 14.2720. Min Act: -0.1700
Data Index: 6974285 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.5220. Min Range: -14.5220
Max Act: 14.2095. Min Act: -0.1700
Data Index: 6855924 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.5220. Min Range: -14.5220
Max Act: 14.1470. Min Act: -0.1700
Data Index: 5405219 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.5220. Min Range: -14.5220
Max Act: 14.0220. Min Act: -0.1700
Data Index: 3114696 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.5220. Min Range: -14.5220
Max Act: 14.0220. Min Act: -0.1700
Data Index: 8751768 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.5220. Min Range: -14.5220
Max Act: 14.0220. Min Act: -0.1700
Data Index: 8069203 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.5220. Min Range: -14.5220
Max Act: 13.8345. Min Act: -0.1700
Data Index: 4026906 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.5220. Min Range: -14.5220
Max Act: 13.7720. Min Act: -0.1700
Data Index: 7392343 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.5220. Min Range: -14.5220
Max Act: 13.8345. Min Act: -0.1700
Data Index: 6214810 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.5220. Min Range: -14.5220
Max Act: 13.8345. Min Act: -0.1700
Data Index: 3316000 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.5220. Min Range: -14.5220
Max Act: 13.7720. Min Act: -0.1700
Data Index: 3367646 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.5220. Min Range: -14.5220
Max Act: 13.7720. Min Act: -0.1700
Data Index: 2402404 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.5220. Min Range: -14.5220
Max Act: 13.7095. Min Act: -0.1700
Data Index: 8707245 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.5220. Min Range: -14.5220
Max Act: 13.7095. Min Act: -0.1700
Data Index: 4894589 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.5220. Min Range: -14.5220
Max Act: 13.7720. Min Act: -0.1700
Data Index: 2345073 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.5220. Min Range: -14.5220
Max Act: 13.7095. Min Act: -0.1700
Data Index: 112380 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #19