Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6389 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4469. Min Range: -7.4469
Max Act: 7.4469. Min Act: -0.1700
Data Index: 6086015 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4469. Min Range: -7.4469
Max Act: 7.2594. Min Act: -0.1700
Data Index: 4897872 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4469. Min Range: -7.4469
Max Act: 7.2282. Min Act: -0.1700
Data Index: 178096 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4469. Min Range: -7.4469
Max Act: 7.1969. Min Act: -0.1700
Data Index: 5222064 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4469. Min Range: -7.4469
Max Act: 7.1969. Min Act: -0.1700
Data Index: 4857721 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4469. Min Range: -7.4469
Max Act: 7.1657. Min Act: -0.1700
Data Index: 645778 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4469. Min Range: -7.4469
Max Act: 7.1344. Min Act: -0.1700
Data Index: 4711427 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4469. Min Range: -7.4469
Max Act: 7.0719. Min Act: -0.1700
Data Index: 3908951 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4469. Min Range: -7.4469
Max Act: 7.0407. Min Act: -0.1700
Data Index: 8037942 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4469. Min Range: -7.4469
Max Act: 7.0407. Min Act: -0.1700
Data Index: 1829910 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4469. Min Range: -7.4469
Max Act: 7.0407. Min Act: -0.1700
Data Index: 1044862 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4469. Min Range: -7.4469
Max Act: 7.0407. Min Act: -0.1700
Data Index: 8560473 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4469. Min Range: -7.4469
Max Act: 7.0094. Min Act: -0.1700
Data Index: 584686 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4469. Min Range: -7.4469
Max Act: 6.9782. Min Act: -0.1700
Data Index: 7619992 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4469. Min Range: -7.4469
Max Act: 6.9782. Min Act: -0.1700
Data Index: 3195533 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4469. Min Range: -7.4469
Max Act: 6.9782. Min Act: -0.1700
Data Index: 6919802 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4469. Min Range: -7.4469
Max Act: 6.9782. Min Act: -0.1700
Data Index: 3398061 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4469. Min Range: -7.4469
Max Act: 6.9469. Min Act: -0.1700
Data Index: 7844792 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4469. Min Range: -7.4469
Max Act: 6.9157. Min Act: -0.1700
Data Index: 3088726 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4469. Min Range: -7.4469
Max Act: 6.9157. Min Act: -0.1700
Data Index: 261452 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #19