Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5844 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2363. Min Range: -6.2363
Max Act: 6.2363. Min Act: -0.1700
Data Index: 2301346 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2363. Min Range: -6.2363
Max Act: 6.1738. Min Act: -0.1700
Data Index: 1426940 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2363. Min Range: -6.2363
Max Act: 6.1425. Min Act: -0.1700
Data Index: 159359 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2363. Min Range: -6.2363
Max Act: 6.1425. Min Act: -0.1700
Data Index: 7588979 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2363. Min Range: -6.2363
Max Act: 6.0800. Min Act: -0.1700
Data Index: 7078970 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2363. Min Range: -6.2363
Max Act: 6.0800. Min Act: -0.1700
Data Index: 7952816 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2363. Min Range: -6.2363
Max Act: 6.0800. Min Act: -0.1700
Data Index: 1269844 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2363. Min Range: -6.2363
Max Act: 6.0488. Min Act: -0.1700
Data Index: 7385537 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2363. Min Range: -6.2363
Max Act: 5.9863. Min Act: -0.1700
Data Index: 5744720 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2363. Min Range: -6.2363
Max Act: 5.9863. Min Act: -0.1700
Data Index: 7807869 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2363. Min Range: -6.2363
Max Act: 5.9550. Min Act: -0.1700
Data Index: 5384736 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2363. Min Range: -6.2363
Max Act: 5.9550. Min Act: -0.1700
Data Index: 6812168 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2363. Min Range: -6.2363
Max Act: 5.9863. Min Act: -0.1700
Data Index: 3955332 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2363. Min Range: -6.2363
Max Act: 5.9550. Min Act: -0.1700
Data Index: 4885149 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2363. Min Range: -6.2363
Max Act: 5.9238. Min Act: -0.1700
Data Index: 3901198 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2363. Min Range: -6.2363
Max Act: 5.8925. Min Act: -0.1700
Data Index: 3028333 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2363. Min Range: -6.2363
Max Act: 5.8925. Min Act: -0.1700
Data Index: 4017634 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2363. Min Range: -6.2363
Max Act: 5.8613. Min Act: -0.1700
Data Index: 4544846 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2363. Min Range: -6.2363
Max Act: 5.8613. Min Act: -0.1700
Data Index: 3728048 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2363. Min Range: -6.2363
Max Act: 5.8925. Min Act: -0.1700
Data Index: 5098683 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #19