Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1023 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7621. Min Range: -7.7621
Max Act: 7.7621. Min Act: -0.1700
Data Index: 4835695 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7621. Min Range: -7.7621
Max Act: 7.6996. Min Act: -0.1700
Data Index: 2381215 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7621. Min Range: -7.7621
Max Act: 7.6371. Min Act: -0.1700
Data Index: 81971 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7621. Min Range: -7.7621
Max Act: 7.5746. Min Act: -0.1700
Data Index: 6443847 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7621. Min Range: -7.7621
Max Act: 7.5434. Min Act: -0.1700
Data Index: 2699009 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7621. Min Range: -7.7621
Max Act: 7.5434. Min Act: -0.1700
Data Index: 5534632 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7621. Min Range: -7.7621
Max Act: 7.4184. Min Act: -0.1700
Data Index: 744377 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7621. Min Range: -7.7621
Max Act: 7.3871. Min Act: -0.1700
Data Index: 831570 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7621. Min Range: -7.7621
Max Act: 7.3871. Min Act: -0.1700
Data Index: 2561503 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7621. Min Range: -7.7621
Max Act: 7.3559. Min Act: -0.1700
Data Index: 3381422 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7621. Min Range: -7.7621
Max Act: 7.3246. Min Act: -0.1700
Data Index: 7819080 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7621. Min Range: -7.7621
Max Act: 7.2934. Min Act: -0.1700
Data Index: 2870535 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7621. Min Range: -7.7621
Max Act: 7.2934. Min Act: -0.1700
Data Index: 5818371 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7621. Min Range: -7.7621
Max Act: 7.2621. Min Act: -0.1700
Data Index: 7917573 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7621. Min Range: -7.7621
Max Act: 7.2934. Min Act: -0.1700
Data Index: 6291619 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7621. Min Range: -7.7621
Max Act: 7.2309. Min Act: -0.1700
Data Index: 2692289 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7621. Min Range: -7.7621
Max Act: 7.2309. Min Act: -0.1700
Data Index: 5918553 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7621. Min Range: -7.7621
Max Act: 7.2309. Min Act: -0.1700
Data Index: 2416374 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7621. Min Range: -7.7621
Max Act: 7.2309. Min Act: -0.1700
Data Index: 6250791 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7621. Min Range: -7.7621
Max Act: 7.1996. Min Act: -0.1700
Data Index: 138396 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19