Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 510 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.5647. Min Act: -0.1700
Data Index: 3523114 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.5959. Min Act: -0.1700
Data Index: 2712865 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.4084. Min Act: -0.1700
Data Index: 2650270 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.2834. Min Act: -0.1700
Data Index: 4624955 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.2522. Min Act: -0.1700
Data Index: 5417235 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.2522. Min Act: -0.1700
Data Index: 6848767 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.1584. Min Act: -0.1700
Data Index: 2716950 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.1272. Min Act: -0.1700
Data Index: 7162756 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.1272. Min Act: -0.1700
Data Index: 5245749 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.0959. Min Act: -0.1700
Data Index: 6255646 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.1272. Min Act: -0.1700
Data Index: 7193959 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.1584. Min Act: -0.1700
Data Index: 883053 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.0959. Min Act: -0.1700
Data Index: 7569866 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.0647. Min Act: -0.1700
Data Index: 4933051 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.0647. Min Act: -0.1700
Data Index: 6847874 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.0647. Min Act: -0.1700
Data Index: 1754042 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.0022. Min Act: -0.1700
Data Index: 1146694 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.0334. Min Act: -0.1700
Data Index: 2678033 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.0022. Min Act: -0.1700
Data Index: 382675 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5959. Min Range: -6.5959
Max Act: 6.0334. Min Act: -0.1700
Data Index: 4417947 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #19