Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4423 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7598. Min Range: -8.7598
Max Act: 8.7598. Min Act: -0.1700
Data Index: 8106331 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7598. Min Range: -8.7598
Max Act: 8.6348. Min Act: -0.1700
Data Index: 6522268 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7598. Min Range: -8.7598
Max Act: 8.6973. Min Act: -0.1700
Data Index: 6352749 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7598. Min Range: -8.7598
Max Act: 8.6973. Min Act: -0.1700
Data Index: 7949814 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7598. Min Range: -8.7598
Max Act: 8.5723. Min Act: -0.1700
Data Index: 3473942 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7598. Min Range: -8.7598
Max Act: 8.5723. Min Act: -0.1700
Data Index: 1565379 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7598. Min Range: -8.7598
Max Act: 8.5723. Min Act: -0.1700
Data Index: 4986954 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7598. Min Range: -8.7598
Max Act: 8.5723. Min Act: -0.1700
Data Index: 839137 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7598. Min Range: -8.7598
Max Act: 8.5098. Min Act: -0.1700
Data Index: 6235314 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7598. Min Range: -8.7598
Max Act: 8.5098. Min Act: -0.1700
Data Index: 1557981 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7598. Min Range: -8.7598
Max Act: 8.5098. Min Act: -0.1700
Data Index: 7914885 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7598. Min Range: -8.7598
Max Act: 8.5098. Min Act: -0.1700
Data Index: 6223488 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7598. Min Range: -8.7598
Max Act: 8.5098. Min Act: -0.1700
Data Index: 4564661 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7598. Min Range: -8.7598
Max Act: 8.5098. Min Act: -0.1700
Data Index: 7214620 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7598. Min Range: -8.7598
Max Act: 8.5098. Min Act: -0.1700
Data Index: 4017654 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7598. Min Range: -8.7598
Max Act: 8.4473. Min Act: -0.1700
Data Index: 7861756 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7598. Min Range: -8.7598
Max Act: 8.4473. Min Act: -0.1700
Data Index: 7341852 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7598. Min Range: -8.7598
Max Act: 8.4473. Min Act: -0.1700
Data Index: 3228837 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7598. Min Range: -8.7598
Max Act: 8.4473. Min Act: -0.1700
Data Index: 474253 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7598. Min Range: -8.7598
Max Act: 8.4473. Min Act: -0.1700
Data Index: 111060 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #19