Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4404 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4425. Min Range: -5.4425
Max Act: 5.4425. Min Act: -0.1700
Data Index: 963491 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4425. Min Range: -5.4425
Max Act: 5.4425. Min Act: -0.1700
Data Index: 5498076 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4425. Min Range: -5.4425
Max Act: 5.4425. Min Act: -0.1700
Data Index: 1192495 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4425. Min Range: -5.4425
Max Act: 5.3800. Min Act: -0.1700
Data Index: 7765504 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4425. Min Range: -5.4425
Max Act: 5.3488. Min Act: -0.1700
Data Index: 3504224 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4425. Min Range: -5.4425
Max Act: 5.3800. Min Act: -0.1700
Data Index: 7209725 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4425. Min Range: -5.4425
Max Act: 5.3488. Min Act: -0.1700
Data Index: 6246097 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4425. Min Range: -5.4425
Max Act: 5.2863. Min Act: -0.1700
Data Index: 7252013 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4425. Min Range: -5.4425
Max Act: 5.2550. Min Act: -0.1700
Data Index: 177155 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4425. Min Range: -5.4425
Max Act: 5.2550. Min Act: -0.1700
Data Index: 6494312 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4425. Min Range: -5.4425
Max Act: 5.2550. Min Act: -0.1700
Data Index: 6282086 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4425. Min Range: -5.4425
Max Act: 5.2550. Min Act: -0.1700
Data Index: 4568380 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4425. Min Range: -5.4425
Max Act: 5.2238. Min Act: -0.1700
Data Index: 3523531 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4425. Min Range: -5.4425
Max Act: 5.1925. Min Act: -0.1700
Data Index: 3723164 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4425. Min Range: -5.4425
Max Act: 5.1613. Min Act: -0.1700
Data Index: 3051733 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4425. Min Range: -5.4425
Max Act: 5.1613. Min Act: -0.1700
Data Index: 6924961 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4425. Min Range: -5.4425
Max Act: 5.1613. Min Act: -0.1700
Data Index: 4095444 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4425. Min Range: -5.4425
Max Act: 5.1300. Min Act: -0.1700
Data Index: 3942363 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4425. Min Range: -5.4425
Max Act: 5.1300. Min Act: -0.1700
Data Index: 1873586 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4425. Min Range: -5.4425
Max Act: 5.1300. Min Act: -0.1700
Data Index: 6888698 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #19