Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3621 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6839. Min Range: -9.6839
Max Act: 9.6839. Min Act: -0.1700
Data Index: 4562409 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6839. Min Range: -9.6839
Max Act: 9.0589. Min Act: -0.1692
Data Index: 5876182 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6839. Min Range: -9.6839
Max Act: 9.0589. Min Act: -0.1700
Data Index: 5001500 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6839. Min Range: -9.6839
Max Act: 8.9964. Min Act: -0.1700
Data Index: 305769 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6839. Min Range: -9.6839
Max Act: 8.9964. Min Act: -0.1700
Data Index: 3080791 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6839. Min Range: -9.6839
Max Act: 8.9339. Min Act: -0.1700
Data Index: 2191371 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6839. Min Range: -9.6839
Max Act: 8.9339. Min Act: -0.1700
Data Index: 7738323 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6839. Min Range: -9.6839
Max Act: 8.9339. Min Act: -0.1700
Data Index: 96389 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6839. Min Range: -9.6839
Max Act: 8.9339. Min Act: -0.1700
Data Index: 678739 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6839. Min Range: -9.6839
Max Act: 8.9339. Min Act: -0.1700
Data Index: 7676780 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6839. Min Range: -9.6839
Max Act: 8.8714. Min Act: -0.1700
Data Index: 4222898 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6839. Min Range: -9.6839
Max Act: 8.8714. Min Act: -0.1699
Data Index: 5122463 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6839. Min Range: -9.6839
Max Act: 8.8714. Min Act: -0.1700
Data Index: 7933609 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6839. Min Range: -9.6839
Max Act: 8.8714. Min Act: -0.1696
Data Index: 2408337 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6839. Min Range: -9.6839
Max Act: 8.8714. Min Act: -0.1690
Data Index: 2151586 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6839. Min Range: -9.6839
Max Act: 8.8714. Min Act: -0.1700
Data Index: 6432987 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6839. Min Range: -9.6839
Max Act: 8.7464. Min Act: -0.1700
Data Index: 7549587 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6839. Min Range: -9.6839
Max Act: 8.8089. Min Act: -0.1700
Data Index: 4701627 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6839. Min Range: -9.6839
Max Act: 8.8089. Min Act: -0.1700
Data Index: 857992 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6839. Min Range: -9.6839
Max Act: 8.7464. Min Act: -0.1699
Data Index: 5122464 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19