Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3477 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5389. Min Range: -6.5389
Max Act: 6.5389. Min Act: -0.1700
Data Index: 1898066 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5389. Min Range: -6.5389
Max Act: 6.4764. Min Act: -0.1700
Data Index: 6349284 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5389. Min Range: -6.5389
Max Act: 6.4452. Min Act: -0.1700
Data Index: 5235400 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5389. Min Range: -6.5389
Max Act: 6.3827. Min Act: -0.1700
Data Index: 7833164 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5389. Min Range: -6.5389
Max Act: 6.3827. Min Act: -0.1700
Data Index: 1701021 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5389. Min Range: -6.5389
Max Act: 6.3514. Min Act: -0.1700
Data Index: 3714997 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5389. Min Range: -6.5389
Max Act: 6.3202. Min Act: -0.1700
Data Index: 3189421 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5389. Min Range: -6.5389
Max Act: 6.3202. Min Act: -0.1700
Data Index: 3120660 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5389. Min Range: -6.5389
Max Act: 6.3514. Min Act: -0.1700
Data Index: 480731 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5389. Min Range: -6.5389
Max Act: 6.2889. Min Act: -0.1700
Data Index: 7138701 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5389. Min Range: -6.5389
Max Act: 6.3202. Min Act: -0.1700
Data Index: 2898688 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5389. Min Range: -6.5389
Max Act: 6.2889. Min Act: -0.1700
Data Index: 3794423 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5389. Min Range: -6.5389
Max Act: 6.2889. Min Act: -0.1700
Data Index: 6215378 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5389. Min Range: -6.5389
Max Act: 6.2577. Min Act: -0.1700
Data Index: 4046621 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5389. Min Range: -6.5389
Max Act: 6.2577. Min Act: -0.1700
Data Index: 1846651 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5389. Min Range: -6.5389
Max Act: 6.2577. Min Act: -0.1700
Data Index: 5796795 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5389. Min Range: -6.5389
Max Act: 6.2577. Min Act: -0.1700
Data Index: 5528890 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5389. Min Range: -6.5389
Max Act: 6.2577. Min Act: -0.1700
Data Index: 3527737 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5389. Min Range: -6.5389
Max Act: 6.2264. Min Act: -0.1700
Data Index: 7822708 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5389. Min Range: -6.5389
Max Act: 6.2264. Min Act: -0.1700
Data Index: 2800600 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19