Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2621 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.7051. Min Act: -0.1700
Data Index: 5596621 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.5801. Min Act: -0.1700
Data Index: 1874025 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.3301. Min Act: -0.1700
Data Index: 4312096 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.2676. Min Act: -0.1700
Data Index: 7483244 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.2676. Min Act: -0.1700
Data Index: 8790889 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.2051. Min Act: -0.1700
Data Index: 1061940 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.1426. Min Act: -0.1700
Data Index: 7228465 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.1426. Min Act: -0.1700
Data Index: 426123 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.2051. Min Act: -0.1700
Data Index: 809789 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.1426. Min Act: -0.1700
Data Index: 3981800 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.0801. Min Act: -0.1700
Data Index: 3460420 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.0176. Min Act: -0.1700
Data Index: 2558476 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.0801. Min Act: -0.1700
Data Index: 7508381 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.0801. Min Act: -0.1700
Data Index: 4238805 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.0801. Min Act: -0.1700
Data Index: 2397242 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.0176. Min Act: -0.1700
Data Index: 5114404 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.0176. Min Act: -0.1700
Data Index: 1808862 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7051. Min Range: -8.7051
Max Act: 8.0176. Min Act: -0.1700
Data Index: 1382652 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7051. Min Range: -8.7051
Max Act: 7.9551. Min Act: -0.1700
Data Index: 4508306 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7051. Min Range: -8.7051
Max Act: 7.9551. Min Act: -0.1700
Data Index: 6200814 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #19