Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3476 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0570. Min Range: -5.0570
Max Act: 5.0570. Min Act: -0.1700
Data Index: 8223632 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0570. Min Range: -5.0570
Max Act: 5.0570. Min Act: -0.1700
Data Index: 1700736 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0570. Min Range: -5.0570
Max Act: 5.0258. Min Act: -0.1700
Data Index: 1791775 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0570. Min Range: -5.0570
Max Act: 5.0570. Min Act: -0.1700
Data Index: 2987321 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0570. Min Range: -5.0570
Max Act: 4.9633. Min Act: -0.1700
Data Index: 8223631 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0570. Min Range: -5.0570
Max Act: 4.9633. Min Act: -0.1700
Data Index: 1587529 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0570. Min Range: -5.0570
Max Act: 4.9320. Min Act: -0.1700
Data Index: 1216991 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0570. Min Range: -5.0570
Max Act: 4.9320. Min Act: -0.1700
Data Index: 2404388 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0570. Min Range: -5.0570
Max Act: 4.9320. Min Act: -0.1700
Data Index: 8359671 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0570. Min Range: -5.0570
Max Act: 4.9320. Min Act: -0.1700
Data Index: 1069524 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0570. Min Range: -5.0570
Max Act: 4.9320. Min Act: -0.1700
Data Index: 2909463 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0570. Min Range: -5.0570
Max Act: 4.9008. Min Act: -0.1700
Data Index: 2644304 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0570. Min Range: -5.0570
Max Act: 4.9320. Min Act: -0.1700
Data Index: 8484737 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0570. Min Range: -5.0570
Max Act: 4.9008. Min Act: -0.1700
Data Index: 3953739 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0570. Min Range: -5.0570
Max Act: 4.9320. Min Act: -0.1700
Data Index: 6462649 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0570. Min Range: -5.0570
Max Act: 4.9320. Min Act: -0.1700
Data Index: 5421031 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0570. Min Range: -5.0570
Max Act: 4.9008. Min Act: -0.1700
Data Index: 1425426 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0570. Min Range: -5.0570
Max Act: 4.9320. Min Act: -0.1700
Data Index: 2359409 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0570. Min Range: -5.0570
Max Act: 4.8695. Min Act: -0.1700
Data Index: 6754662 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0570. Min Range: -5.0570
Max Act: 4.8695. Min Act: -0.1700
Data Index: 1411282 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19