Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4058 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7517. Min Range: -4.7517
Max Act: 4.7517. Min Act: -0.1700
Data Index: 68757 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7517. Min Range: -4.7517
Max Act: 4.7517. Min Act: -0.1700
Data Index: 1078508 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7517. Min Range: -4.7517
Max Act: 4.7205. Min Act: -0.1700
Data Index: 350348 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7517. Min Range: -4.7517
Max Act: 4.6892. Min Act: -0.1700
Data Index: 2525230 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7517. Min Range: -4.7517
Max Act: 4.7205. Min Act: -0.1700
Data Index: 3832516 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7517. Min Range: -4.7517
Max Act: 4.6892. Min Act: -0.1700
Data Index: 8281458 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7517. Min Range: -4.7517
Max Act: 4.6892. Min Act: -0.1700
Data Index: 461733 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7517. Min Range: -4.7517
Max Act: 4.6892. Min Act: -0.1700
Data Index: 7205904 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7517. Min Range: -4.7517
Max Act: 4.6892. Min Act: -0.1700
Data Index: 2137255 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7517. Min Range: -4.7517
Max Act: 4.6267. Min Act: -0.1700
Data Index: 4719817 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7517. Min Range: -4.7517
Max Act: 4.6267. Min Act: -0.1700
Data Index: 3064492 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7517. Min Range: -4.7517
Max Act: 4.6580. Min Act: -0.1700
Data Index: 3968429 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7517. Min Range: -4.7517
Max Act: 4.6580. Min Act: -0.1700
Data Index: 2501698 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7517. Min Range: -4.7517
Max Act: 4.6580. Min Act: -0.1700
Data Index: 3710571 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7517. Min Range: -4.7517
Max Act: 4.6580. Min Act: -0.1700
Data Index: 443449 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7517. Min Range: -4.7517
Max Act: 4.6267. Min Act: -0.1700
Data Index: 3680756 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7517. Min Range: -4.7517
Max Act: 4.6267. Min Act: -0.1700
Data Index: 610976 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7517. Min Range: -4.7517
Max Act: 4.6267. Min Act: -0.1700
Data Index: 3542676 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7517. Min Range: -4.7517
Max Act: 4.6267. Min Act: -0.1700
Data Index: 4803824 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7517. Min Range: -4.7517
Max Act: 4.6267. Min Act: -0.1700
Data Index: 1806289 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19