Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 576 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6784. Min Range: -4.6784
Max Act: 4.6784. Min Act: -0.1700
Data Index: 7855774 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6784. Min Range: -4.6784
Max Act: 4.6471. Min Act: -0.1700
Data Index: 7752829 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6784. Min Range: -4.6784
Max Act: 4.5534. Min Act: -0.1700
Data Index: 8459052 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6784. Min Range: -4.6784
Max Act: 4.5221. Min Act: -0.1700
Data Index: 4541454 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6784. Min Range: -4.6784
Max Act: 4.5221. Min Act: -0.1700
Data Index: 1812653 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6784. Min Range: -4.6784
Max Act: 4.5221. Min Act: -0.1700
Data Index: 6990449 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6784. Min Range: -4.6784
Max Act: 4.4909. Min Act: -0.1700
Data Index: 7359072 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6784. Min Range: -4.6784
Max Act: 4.5221. Min Act: -0.1700
Data Index: 5303991 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6784. Min Range: -4.6784
Max Act: 4.4909. Min Act: -0.1700
Data Index: 2141415 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6784. Min Range: -4.6784
Max Act: 4.4909. Min Act: -0.1700
Data Index: 7507816 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6784. Min Range: -4.6784
Max Act: 4.5221. Min Act: -0.1700
Data Index: 4469251 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6784. Min Range: -4.6784
Max Act: 4.4596. Min Act: -0.1700
Data Index: 5773663 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6784. Min Range: -4.6784
Max Act: 4.4284. Min Act: -0.1700
Data Index: 5465641 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6784. Min Range: -4.6784
Max Act: 4.4596. Min Act: -0.1700
Data Index: 4169155 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6784. Min Range: -4.6784
Max Act: 4.4284. Min Act: -0.1700
Data Index: 2307382 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6784. Min Range: -4.6784
Max Act: 4.3971. Min Act: -0.1700
Data Index: 4883630 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6784. Min Range: -4.6784
Max Act: 4.3971. Min Act: -0.1700
Data Index: 7046258 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6784. Min Range: -4.6784
Max Act: 4.3971. Min Act: -0.1700
Data Index: 7641368 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6784. Min Range: -4.6784
Max Act: 4.3971. Min Act: -0.1700
Data Index: 1887225 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6784. Min Range: -4.6784
Max Act: 4.3971. Min Act: -0.1700
Data Index: 6394403 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #19