Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1113 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6892. Min Range: -8.6892
Max Act: 8.6892. Min Act: -0.1700
Data Index: 4061705 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6892. Min Range: -8.6892
Max Act: 8.5017. Min Act: -0.1700
Data Index: 1341333 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6892. Min Range: -8.6892
Max Act: 8.4392. Min Act: -0.1700
Data Index: 189982 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6892. Min Range: -8.6892
Max Act: 8.3767. Min Act: -0.1700
Data Index: 6165155 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6892. Min Range: -8.6892
Max Act: 8.3767. Min Act: -0.1700
Data Index: 2327066 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6892. Min Range: -8.6892
Max Act: 8.3767. Min Act: -0.1700
Data Index: 4521971 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6892. Min Range: -8.6892
Max Act: 8.3767. Min Act: -0.1700
Data Index: 6386390 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6892. Min Range: -8.6892
Max Act: 8.3767. Min Act: -0.1700
Data Index: 3224226 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6892. Min Range: -8.6892
Max Act: 8.3767. Min Act: -0.1700
Data Index: 8319611 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6892. Min Range: -8.6892
Max Act: 8.3767. Min Act: -0.1700
Data Index: 5487280 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6892. Min Range: -8.6892
Max Act: 8.1892. Min Act: -0.1700
Data Index: 4026716 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6892. Min Range: -8.6892
Max Act: 8.1267. Min Act: -0.1700
Data Index: 3344376 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6892. Min Range: -8.6892
Max Act: 8.1267. Min Act: -0.1700
Data Index: 774676 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6892. Min Range: -8.6892
Max Act: 8.1267. Min Act: -0.1700
Data Index: 4868739 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6892. Min Range: -8.6892
Max Act: 8.1267. Min Act: -0.1700
Data Index: 2695930 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6892. Min Range: -8.6892
Max Act: 8.0642. Min Act: -0.1700
Data Index: 3782695 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6892. Min Range: -8.6892
Max Act: 8.0642. Min Act: -0.1700
Data Index: 3738862 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6892. Min Range: -8.6892
Max Act: 8.0642. Min Act: -0.1700
Data Index: 6053732 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6892. Min Range: -8.6892
Max Act: 8.0642. Min Act: -0.1700
Data Index: 5487209 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6892. Min Range: -8.6892
Max Act: 8.0017. Min Act: -0.1700
Data Index: 2116290 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #19