Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3264 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3031. Min Range: -6.3031
Max Act: 6.3031. Min Act: -0.1700
Data Index: 7381426 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3031. Min Range: -6.3031
Max Act: 6.1781. Min Act: -0.1700
Data Index: 516701 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3031. Min Range: -6.3031
Max Act: 6.0844. Min Act: -0.1700
Data Index: 4056405 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3031. Min Range: -6.3031
Max Act: 6.0531. Min Act: -0.1700
Data Index: 2677351 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3031. Min Range: -6.3031
Max Act: 6.0219. Min Act: -0.1700
Data Index: 5134807 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3031. Min Range: -6.3031
Max Act: 5.9906. Min Act: -0.1700
Data Index: 7448532 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3031. Min Range: -6.3031
Max Act: 5.9906. Min Act: -0.1700
Data Index: 3488652 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3031. Min Range: -6.3031
Max Act: 5.9281. Min Act: -0.1700
Data Index: 5452272 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3031. Min Range: -6.3031
Max Act: 5.9594. Min Act: -0.1700
Data Index: 8626622 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3031. Min Range: -6.3031
Max Act: 5.8969. Min Act: -0.1700
Data Index: 4002398 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3031. Min Range: -6.3031
Max Act: 5.8969. Min Act: -0.1700
Data Index: 2114276 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3031. Min Range: -6.3031
Max Act: 5.8969. Min Act: -0.1700
Data Index: 6283881 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3031. Min Range: -6.3031
Max Act: 5.8969. Min Act: -0.1700
Data Index: 8228990 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3031. Min Range: -6.3031
Max Act: 5.8344. Min Act: -0.1700
Data Index: 7212898 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3031. Min Range: -6.3031
Max Act: 5.8344. Min Act: -0.1700
Data Index: 4267902 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3031. Min Range: -6.3031
Max Act: 5.8031. Min Act: -0.1700
Data Index: 2266377 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3031. Min Range: -6.3031
Max Act: 5.8031. Min Act: -0.1700
Data Index: 2638745 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3031. Min Range: -6.3031
Max Act: 5.7719. Min Act: -0.1700
Data Index: 5090460 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3031. Min Range: -6.3031
Max Act: 5.7719. Min Act: -0.1700
Data Index: 3576807 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3031. Min Range: -6.3031
Max Act: 5.7719. Min Act: -0.1700
Data Index: 515954 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19