Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2333 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.7923. Min Act: -0.1700
Data Index: 1659995 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.7611. Min Act: -0.1700
Data Index: 6445041 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.5423. Min Act: -0.1700
Data Index: 7994634 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.5111. Min Act: -0.1700
Data Index: 5573497 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.4798. Min Act: -0.1700
Data Index: 3363926 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.4798. Min Act: -0.1700
Data Index: 1624732 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.3861. Min Act: -0.1700
Data Index: 7047475 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.4173. Min Act: -0.1700
Data Index: 4309536 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.3548. Min Act: -0.1700
Data Index: 7218981 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.3236. Min Act: -0.1700
Data Index: 284519 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.3236. Min Act: -0.1700
Data Index: 1025190 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.3236. Min Act: -0.1700
Data Index: 4696509 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.3236. Min Act: -0.1700
Data Index: 3352278 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.3548. Min Act: -0.1700
Data Index: 7556304 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.2923. Min Act: -0.1700
Data Index: 2420889 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.2611. Min Act: -0.1700
Data Index: 4393762 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.2611. Min Act: -0.1700
Data Index: 1579526 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.2923. Min Act: -0.1700
Data Index: 637092 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.2611. Min Act: -0.1700
Data Index: 5042792 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7923. Min Range: -5.7923
Max Act: 5.2923. Min Act: -0.1700
Data Index: 6374697 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #19