Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3020 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.4576. Min Act: -0.1700
Data Index: 598858 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.4263. Min Act: -0.1700
Data Index: 1921043 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.3949. Min Act: -0.1700
Data Index: 2864379 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.3322. Min Act: -0.1700
Data Index: 6909199 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.3165. Min Act: -0.1700
Data Index: 2471334 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.3322. Min Act: -0.1700
Data Index: 388459 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.3165. Min Act: -0.1700
Data Index: 7361135 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.3008. Min Act: -0.1700
Data Index: 3119427 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.2851. Min Act: -0.1700
Data Index: 518162 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.2694. Min Act: -0.1700
Data Index: 3582672 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.2851. Min Act: -0.1700
Data Index: 6239682 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.2537. Min Act: -0.1700
Data Index: 2465200 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.2537. Min Act: -0.1700
Data Index: 2991519 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.2537. Min Act: -0.1700
Data Index: 4868860 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.2537. Min Act: -0.1700
Data Index: 8223539 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.2379. Min Act: -0.1700
Data Index: 7921764 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.2379. Min Act: -0.1700
Data Index: 1260454 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.2379. Min Act: -0.1700
Data Index: 4111135 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.2222. Min Act: -0.1700
Data Index: 8360786 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4576. Min Range: -3.4576
Max Act: 3.2379. Min Act: -0.1700
Data Index: 6223957 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19