Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2890 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1222. Min Range: -6.1222
Max Act: 6.1222. Min Act: -0.1700
Data Index: 3553387 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1222. Min Range: -6.1222
Max Act: 6.0910. Min Act: -0.1700
Data Index: 3507036 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1222. Min Range: -6.1222
Max Act: 5.9972. Min Act: -0.1700
Data Index: 6372584 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1222. Min Range: -6.1222
Max Act: 5.9972. Min Act: -0.1700
Data Index: 678561 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1222. Min Range: -6.1222
Max Act: 5.9660. Min Act: -0.1700
Data Index: 972074 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1222. Min Range: -6.1222
Max Act: 5.9660. Min Act: -0.1700
Data Index: 3821701 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1222. Min Range: -6.1222
Max Act: 5.9660. Min Act: -0.1700
Data Index: 7786907 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1222. Min Range: -6.1222
Max Act: 5.9035. Min Act: -0.1700
Data Index: 6028039 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1222. Min Range: -6.1222
Max Act: 5.8722. Min Act: -0.1700
Data Index: 3178318 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1222. Min Range: -6.1222
Max Act: 5.8722. Min Act: -0.1700
Data Index: 7487564 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1222. Min Range: -6.1222
Max Act: 5.8410. Min Act: -0.1700
Data Index: 5135069 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1222. Min Range: -6.1222
Max Act: 5.8410. Min Act: -0.1700
Data Index: 1833160 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1222. Min Range: -6.1222
Max Act: 5.8410. Min Act: -0.1700
Data Index: 7260331 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1222. Min Range: -6.1222
Max Act: 5.8097. Min Act: -0.1700
Data Index: 8304218 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1222. Min Range: -6.1222
Max Act: 5.8097. Min Act: -0.1700
Data Index: 5199246 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1222. Min Range: -6.1222
Max Act: 5.8097. Min Act: -0.1700
Data Index: 8264910 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1222. Min Range: -6.1222
Max Act: 5.8097. Min Act: -0.1700
Data Index: 5988813 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1222. Min Range: -6.1222
Max Act: 5.8097. Min Act: -0.1700
Data Index: 5598936 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1222. Min Range: -6.1222
Max Act: 5.8097. Min Act: -0.1700
Data Index: 5143432 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1222. Min Range: -6.1222
Max Act: 5.7472. Min Act: -0.1700
Data Index: 1965420 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #19