Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3098 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0318. Min Range: -6.0318
Max Act: 6.0318. Min Act: -0.1700
Data Index: 4675910 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0318. Min Range: -6.0318
Max Act: 5.9381. Min Act: -0.1700
Data Index: 5541136 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0318. Min Range: -6.0318
Max Act: 5.9693. Min Act: -0.1700
Data Index: 5727904 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0318. Min Range: -6.0318
Max Act: 5.9068. Min Act: -0.1700
Data Index: 3307921 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0318. Min Range: -6.0318
Max Act: 5.9381. Min Act: -0.1700
Data Index: 8607604 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0318. Min Range: -6.0318
Max Act: 5.8756. Min Act: -0.1700
Data Index: 6541544 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0318. Min Range: -6.0318
Max Act: 5.8756. Min Act: -0.1700
Data Index: 3779657 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0318. Min Range: -6.0318
Max Act: 5.8443. Min Act: -0.1700
Data Index: 692624 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0318. Min Range: -6.0318
Max Act: 5.8443. Min Act: -0.1700
Data Index: 8387078 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0318. Min Range: -6.0318
Max Act: 5.8443. Min Act: -0.1700
Data Index: 3991698 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0318. Min Range: -6.0318
Max Act: 5.8131. Min Act: -0.1700
Data Index: 7989978 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0318. Min Range: -6.0318
Max Act: 5.7818. Min Act: -0.1700
Data Index: 7461304 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0318. Min Range: -6.0318
Max Act: 5.7193. Min Act: -0.1700
Data Index: 3497057 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0318. Min Range: -6.0318
Max Act: 5.7193. Min Act: -0.1700
Data Index: 4472767 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0318. Min Range: -6.0318
Max Act: 5.7193. Min Act: -0.1700
Data Index: 7640927 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0318. Min Range: -6.0318
Max Act: 5.7193. Min Act: -0.1700
Data Index: 322246 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0318. Min Range: -6.0318
Max Act: 5.6256. Min Act: -0.1700
Data Index: 3408630 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0318. Min Range: -6.0318
Max Act: 5.6568. Min Act: -0.1700
Data Index: 361701 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0318. Min Range: -6.0318
Max Act: 5.6881. Min Act: -0.1700
Data Index: 5789886 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0318. Min Range: -6.0318
Max Act: 5.6881. Min Act: -0.1700
Data Index: 1975777 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #19