Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5172 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4193. Min Range: -5.4193
Max Act: 5.4193. Min Act: -0.1700
Data Index: 6906893 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4193. Min Range: -5.4193
Max Act: 5.3568. Min Act: -0.1700
Data Index: 8020352 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4193. Min Range: -5.4193
Max Act: 5.3568. Min Act: -0.1700
Data Index: 3347120 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4193. Min Range: -5.4193
Max Act: 5.3255. Min Act: -0.1700
Data Index: 7175225 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4193. Min Range: -5.4193
Max Act: 5.2630. Min Act: -0.1700
Data Index: 1863600 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4193. Min Range: -5.4193
Max Act: 5.2630. Min Act: -0.1700
Data Index: 185125 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4193. Min Range: -5.4193
Max Act: 5.2630. Min Act: -0.1700
Data Index: 1899252 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4193. Min Range: -5.4193
Max Act: 5.2630. Min Act: -0.1700
Data Index: 6176277 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4193. Min Range: -5.4193
Max Act: 5.2318. Min Act: -0.1700
Data Index: 7681030 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4193. Min Range: -5.4193
Max Act: 5.2318. Min Act: -0.1700
Data Index: 2634485 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4193. Min Range: -5.4193
Max Act: 5.2318. Min Act: -0.1700
Data Index: 6036478 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4193. Min Range: -5.4193
Max Act: 5.2318. Min Act: -0.1700
Data Index: 5468431 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4193. Min Range: -5.4193
Max Act: 5.2318. Min Act: -0.1700
Data Index: 1183847 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4193. Min Range: -5.4193
Max Act: 5.2318. Min Act: -0.1700
Data Index: 821595 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4193. Min Range: -5.4193
Max Act: 5.2318. Min Act: -0.1700
Data Index: 7945919 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4193. Min Range: -5.4193
Max Act: 5.2318. Min Act: -0.1700
Data Index: 6092055 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4193. Min Range: -5.4193
Max Act: 5.2005. Min Act: -0.1700
Data Index: 7001192 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4193. Min Range: -5.4193
Max Act: 5.2005. Min Act: -0.1700
Data Index: 1442772 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4193. Min Range: -5.4193
Max Act: 5.2005. Min Act: -0.1700
Data Index: 4683256 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4193. Min Range: -5.4193
Max Act: 5.2005. Min Act: -0.1700
Data Index: 2130263 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #19