Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3664 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4899. Min Range: -7.4899
Max Act: 7.4899. Min Act: -0.1700
Data Index: 5770508 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4899. Min Range: -7.4899
Max Act: 7.3337. Min Act: -0.1700
Data Index: 289800 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4899. Min Range: -7.4899
Max Act: 7.0524. Min Act: -0.1700
Data Index: 349240 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4899. Min Range: -7.4899
Max Act: 7.0524. Min Act: -0.1700
Data Index: 1125242 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4899. Min Range: -7.4899
Max Act: 6.9587. Min Act: -0.1700
Data Index: 3319365 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4899. Min Range: -7.4899
Max Act: 6.8962. Min Act: -0.1700
Data Index: 8654903 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4899. Min Range: -7.4899
Max Act: 6.9274. Min Act: -0.1700
Data Index: 7514586 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4899. Min Range: -7.4899
Max Act: 6.8962. Min Act: -0.1700
Data Index: 3173679 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4899. Min Range: -7.4899
Max Act: 6.8962. Min Act: -0.1700
Data Index: 4710576 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4899. Min Range: -7.4899
Max Act: 6.8649. Min Act: -0.1700
Data Index: 8480509 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4899. Min Range: -7.4899
Max Act: 6.8337. Min Act: -0.1700
Data Index: 8798774 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4899. Min Range: -7.4899
Max Act: 6.8024. Min Act: -0.1700
Data Index: 1467287 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4899. Min Range: -7.4899
Max Act: 6.8024. Min Act: -0.1700
Data Index: 6101457 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4899. Min Range: -7.4899
Max Act: 6.7712. Min Act: -0.1700
Data Index: 6380279 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4899. Min Range: -7.4899
Max Act: 6.7087. Min Act: -0.1700
Data Index: 3458326 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4899. Min Range: -7.4899
Max Act: 6.7399. Min Act: -0.1700
Data Index: 7172110 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4899. Min Range: -7.4899
Max Act: 6.7087. Min Act: -0.1700
Data Index: 2679301 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4899. Min Range: -7.4899
Max Act: 6.7087. Min Act: -0.1700
Data Index: 1483752 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4899. Min Range: -7.4899
Max Act: 6.7087. Min Act: -0.1700
Data Index: 2195971 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4899. Min Range: -7.4899
Max Act: 6.7087. Min Act: -0.1700
Data Index: 7311172 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19