Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 38 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1665. Min Range: -7.1665
Max Act: 7.1665. Min Act: -0.1700
Data Index: 3165549 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1665. Min Range: -7.1665
Max Act: 7.0415. Min Act: -0.1700
Data Index: 5185274 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1665. Min Range: -7.1665
Max Act: 7.0102. Min Act: -0.1700
Data Index: 6097337 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1665. Min Range: -7.1665
Max Act: 7.0102. Min Act: -0.1700
Data Index: 8387729 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1665. Min Range: -7.1665
Max Act: 7.0415. Min Act: -0.1700
Data Index: 7260276 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1665. Min Range: -7.1665
Max Act: 6.9477. Min Act: -0.1700
Data Index: 6097340 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1665. Min Range: -7.1665
Max Act: 6.8852. Min Act: -0.1700
Data Index: 6097338 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1665. Min Range: -7.1665
Max Act: 6.9165. Min Act: -0.1700
Data Index: 1954261 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1665. Min Range: -7.1665
Max Act: 6.9477. Min Act: -0.1700
Data Index: 6328989 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1665. Min Range: -7.1665
Max Act: 6.9165. Min Act: -0.1700
Data Index: 5185271 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1665. Min Range: -7.1665
Max Act: 6.8852. Min Act: -0.1700
Data Index: 769842 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1665. Min Range: -7.1665
Max Act: 6.8540. Min Act: -0.1700
Data Index: 6360128 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1665. Min Range: -7.1665
Max Act: 6.8540. Min Act: -0.1700
Data Index: 1621036 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1665. Min Range: -7.1665
Max Act: 6.7915. Min Act: -0.1700
Data Index: 8326355 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1665. Min Range: -7.1665
Max Act: 6.7602. Min Act: -0.1700
Data Index: 8581662 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1665. Min Range: -7.1665
Max Act: 6.7915. Min Act: -0.1700
Data Index: 7195498 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1665. Min Range: -7.1665
Max Act: 6.7290. Min Act: -0.1700
Data Index: 6229352 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1665. Min Range: -7.1665
Max Act: 6.7915. Min Act: -0.1700
Data Index: 3408975 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1665. Min Range: -7.1665
Max Act: 6.7602. Min Act: -0.1700
Data Index: 3572378 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1665. Min Range: -7.1665
Max Act: 6.7602. Min Act: -0.1700
Data Index: 5185269 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19