Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2771 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4477. Min Range: -7.4477
Max Act: 7.4477. Min Act: -0.1700
Data Index: 7283971 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4477. Min Range: -7.4477
Max Act: 7.3227. Min Act: -0.1700
Data Index: 3367508 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4477. Min Range: -7.4477
Max Act: 7.2289. Min Act: -0.1700
Data Index: 8584910 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4477. Min Range: -7.4477
Max Act: 7.2289. Min Act: -0.1700
Data Index: 1725010 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4477. Min Range: -7.4477
Max Act: 7.1664. Min Act: -0.1700
Data Index: 2080201 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4477. Min Range: -7.4477
Max Act: 7.1039. Min Act: -0.1700
Data Index: 3162175 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4477. Min Range: -7.4477
Max Act: 7.0727. Min Act: -0.1700
Data Index: 1263650 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4477. Min Range: -7.4477
Max Act: 7.1039. Min Act: -0.1700
Data Index: 6360595 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4477. Min Range: -7.4477
Max Act: 7.0727. Min Act: -0.1700
Data Index: 5953668 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4477. Min Range: -7.4477
Max Act: 7.0414. Min Act: -0.1700
Data Index: 879567 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4477. Min Range: -7.4477
Max Act: 7.0102. Min Act: -0.1700
Data Index: 3851723 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4477. Min Range: -7.4477
Max Act: 7.0102. Min Act: -0.1700
Data Index: 214911 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4477. Min Range: -7.4477
Max Act: 7.0102. Min Act: -0.1700
Data Index: 208704 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4477. Min Range: -7.4477
Max Act: 7.0102. Min Act: -0.1700
Data Index: 2091140 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4477. Min Range: -7.4477
Max Act: 6.9789. Min Act: -0.1700
Data Index: 3513592 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4477. Min Range: -7.4477
Max Act: 6.9789. Min Act: -0.1700
Data Index: 6024737 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4477. Min Range: -7.4477
Max Act: 6.9789. Min Act: -0.1700
Data Index: 8614466 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4477. Min Range: -7.4477
Max Act: 6.9789. Min Act: -0.1700
Data Index: 197603 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4477. Min Range: -7.4477
Max Act: 6.9477. Min Act: -0.1700
Data Index: 2915930 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4477. Min Range: -7.4477
Max Act: 6.9477. Min Act: -0.1700
Data Index: 4280169 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19