Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5334 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6724. Min Range: -4.6724
Max Act: 4.6724. Min Act: -0.1700
Data Index: 432542 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6724. Min Range: -4.6724
Max Act: 4.6724. Min Act: -0.1700
Data Index: 5161593 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6724. Min Range: -4.6724
Max Act: 4.6099. Min Act: -0.1700
Data Index: 4671669 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6724. Min Range: -4.6724
Max Act: 4.6099. Min Act: -0.1700
Data Index: 8221428 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6724. Min Range: -4.6724
Max Act: 4.6099. Min Act: -0.1700
Data Index: 823887 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6724. Min Range: -4.6724
Max Act: 4.6099. Min Act: -0.1700
Data Index: 6802553 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6724. Min Range: -4.6724
Max Act: 4.6099. Min Act: -0.1700
Data Index: 5227927 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6724. Min Range: -4.6724
Max Act: 4.6099. Min Act: -0.1700
Data Index: 3134579 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6724. Min Range: -4.6724
Max Act: 4.5786. Min Act: -0.1700
Data Index: 2800329 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6724. Min Range: -4.6724
Max Act: 4.5786. Min Act: -0.1700
Data Index: 801935 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6724. Min Range: -4.6724
Max Act: 4.5474. Min Act: -0.1700
Data Index: 8626024 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6724. Min Range: -4.6724
Max Act: 4.5161. Min Act: -0.1700
Data Index: 1991441 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6724. Min Range: -4.6724
Max Act: 4.5161. Min Act: -0.1700
Data Index: 932244 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6724. Min Range: -4.6724
Max Act: 4.5161. Min Act: -0.1700
Data Index: 1924577 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6724. Min Range: -4.6724
Max Act: 4.4849. Min Act: -0.1700
Data Index: 211123 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6724. Min Range: -4.6724
Max Act: 4.4849. Min Act: -0.1700
Data Index: 7482889 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6724. Min Range: -4.6724
Max Act: 4.4849. Min Act: -0.1700
Data Index: 2567637 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6724. Min Range: -4.6724
Max Act: 4.4536. Min Act: -0.1700
Data Index: 4744771 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6724. Min Range: -4.6724
Max Act: 4.4536. Min Act: -0.1700
Data Index: 1794933 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6724. Min Range: -4.6724
Max Act: 4.4536. Min Act: -0.1700
Data Index: 6291631 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19