Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3509 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4308. Min Range: -6.4308
Max Act: 6.4308. Min Act: -0.1700
Data Index: 1603697 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4308. Min Range: -6.4308
Max Act: 6.3683. Min Act: -0.1700
Data Index: 8075371 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4308. Min Range: -6.4308
Max Act: 6.0870. Min Act: -0.1700
Data Index: 7183857 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4308. Min Range: -6.4308
Max Act: 6.0558. Min Act: -0.1700
Data Index: 4641738 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4308. Min Range: -6.4308
Max Act: 6.0870. Min Act: -0.1700
Data Index: 2783388 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4308. Min Range: -6.4308
Max Act: 6.0245. Min Act: -0.1700
Data Index: 1862630 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4308. Min Range: -6.4308
Max Act: 6.0245. Min Act: -0.1700
Data Index: 142358 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4308. Min Range: -6.4308
Max Act: 6.0558. Min Act: -0.1700
Data Index: 7822686 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4308. Min Range: -6.4308
Max Act: 6.0558. Min Act: -0.1700
Data Index: 3811774 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.9933. Min Act: -0.1700
Data Index: 4201238 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.9933. Min Act: -0.1700
Data Index: 7414613 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.9933. Min Act: -0.1700
Data Index: 1339759 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.9933. Min Act: -0.1700
Data Index: 559820 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.9620. Min Act: -0.1700
Data Index: 3191679 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.9620. Min Act: -0.1700
Data Index: 904828 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.9620. Min Act: -0.1700
Data Index: 2527659 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.9308. Min Act: -0.1700
Data Index: 5861971 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.9308. Min Act: -0.1700
Data Index: 5470807 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.8995. Min Act: -0.1700
Data Index: 1747931 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4308. Min Range: -6.4308
Max Act: 5.9620. Min Act: -0.1700
Data Index: 4779629 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19