Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3391 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.7350. Min Act: -0.1700
Data Index: 7362863 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.6100. Min Act: -0.1700
Data Index: 8516842 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.5788. Min Act: -0.1700
Data Index: 3738723 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.5475. Min Act: -0.1700
Data Index: 4207802 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.4538. Min Act: -0.1700
Data Index: 1340518 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.3600. Min Act: -0.1700
Data Index: 1893035 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.3912. Min Act: -0.1700
Data Index: 4841482 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.3912. Min Act: -0.1700
Data Index: 5622449 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.3600. Min Act: -0.1700
Data Index: 4207800 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.3287. Min Act: -0.1700
Data Index: 6543379 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.2975. Min Act: -0.1700
Data Index: 4678446 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.2975. Min Act: -0.1700
Data Index: 7573766 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.2975. Min Act: -0.1700
Data Index: 90631 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.2350. Min Act: -0.1700
Data Index: 6574643 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.2037. Min Act: -0.1700
Data Index: 5618961 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.2037. Min Act: -0.1700
Data Index: 7508825 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.2037. Min Act: -0.1700
Data Index: 2032634 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.1725. Min Act: -0.1700
Data Index: 5263936 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.1725. Min Act: -0.1700
Data Index: 7534377 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7350. Min Range: -4.7350
Max Act: 4.1725. Min Act: -0.1700
Data Index: 1656976 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19