Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3903 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9813. Min Range: -7.9813
Max Act: 7.9813. Min Act: -0.1700
Data Index: 948139 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9813. Min Range: -7.9813
Max Act: 7.9813. Min Act: -0.1700
Data Index: 4192623 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9813. Min Range: -7.9813
Max Act: 7.9188. Min Act: -0.1700
Data Index: 6664000 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9813. Min Range: -7.9813
Max Act: 7.9188. Min Act: -0.1700
Data Index: 7508833 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9813. Min Range: -7.9813
Max Act: 7.7938. Min Act: -0.1700
Data Index: 8011695 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9813. Min Range: -7.9813
Max Act: 7.6688. Min Act: -0.1700
Data Index: 7381488 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9813. Min Range: -7.9813
Max Act: 7.6063. Min Act: -0.1700
Data Index: 8154240 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9813. Min Range: -7.9813
Max Act: 7.6063. Min Act: -0.1700
Data Index: 914561 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9813. Min Range: -7.9813
Max Act: 7.6063. Min Act: -0.1700
Data Index: 1167539 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9813. Min Range: -7.9813
Max Act: 7.5750. Min Act: -0.1700
Data Index: 8092363 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9813. Min Range: -7.9813
Max Act: 7.5750. Min Act: -0.1700
Data Index: 2526889 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9813. Min Range: -7.9813
Max Act: 7.5438. Min Act: -0.1700
Data Index: 6345737 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9813. Min Range: -7.9813
Max Act: 7.6063. Min Act: -0.1700
Data Index: 5514136 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9813. Min Range: -7.9813
Max Act: 7.5438. Min Act: -0.1700
Data Index: 155529 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9813. Min Range: -7.9813
Max Act: 7.5750. Min Act: -0.1700
Data Index: 8036707 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9813. Min Range: -7.9813
Max Act: 7.5125. Min Act: -0.1700
Data Index: 2983303 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9813. Min Range: -7.9813
Max Act: 7.4813. Min Act: -0.1700
Data Index: 1390258 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9813. Min Range: -7.9813
Max Act: 7.5438. Min Act: -0.1700
Data Index: 2696289 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9813. Min Range: -7.9813
Max Act: 7.5125. Min Act: -0.1700
Data Index: 2834485 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9813. Min Range: -7.9813
Max Act: 7.5125. Min Act: -0.1700
Data Index: 2910756 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #19