Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6150 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5844. Min Range: -8.5844
Max Act: 8.5844. Min Act: -0.1700
Data Index: 4795569 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5844. Min Range: -8.5844
Max Act: 8.5219. Min Act: -0.1700
Data Index: 3911492 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5844. Min Range: -8.5844
Max Act: 8.3969. Min Act: -0.1700
Data Index: 6362819 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5844. Min Range: -8.5844
Max Act: 8.2719. Min Act: -0.1700
Data Index: 7640100 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5844. Min Range: -8.5844
Max Act: 7.8969. Min Act: -0.1700
Data Index: 4504466 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5844. Min Range: -8.5844
Max Act: 7.8344. Min Act: -0.1700
Data Index: 6563674 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5844. Min Range: -8.5844
Max Act: 7.8344. Min Act: -0.1700
Data Index: 6592328 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5844. Min Range: -8.5844
Max Act: 7.7094. Min Act: -0.1700
Data Index: 7923545 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5844. Min Range: -8.5844
Max Act: 7.6469. Min Act: -0.1700
Data Index: 815880 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5844. Min Range: -8.5844
Max Act: 7.6156. Min Act: -0.1700
Data Index: 8683054 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5844. Min Range: -8.5844
Max Act: 7.6156. Min Act: -0.1700
Data Index: 5487373 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5844. Min Range: -8.5844
Max Act: 7.5531. Min Act: -0.1700
Data Index: 7595870 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5844. Min Range: -8.5844
Max Act: 7.5531. Min Act: -0.1700
Data Index: 4855982 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5844. Min Range: -8.5844
Max Act: 7.5531. Min Act: -0.1700
Data Index: 6900852 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5844. Min Range: -8.5844
Max Act: 7.5219. Min Act: -0.1700
Data Index: 1249979 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5844. Min Range: -8.5844
Max Act: 7.5219. Min Act: -0.1700
Data Index: 7062161 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5844. Min Range: -8.5844
Max Act: 7.4906. Min Act: -0.1700
Data Index: 4258224 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5844. Min Range: -8.5844
Max Act: 7.4906. Min Act: -0.1700
Data Index: 158399 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5844. Min Range: -8.5844
Max Act: 7.4906. Min Act: -0.1700
Data Index: 5509410 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5844. Min Range: -8.5844
Max Act: 7.4594. Min Act: -0.1700
Data Index: 7085867 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19