Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4114 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3949. Min Range: -8.3949
Max Act: 8.3949. Min Act: -0.1700
Data Index: 6638509 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3949. Min Range: -8.3949
Max Act: 8.1449. Min Act: -0.1700
Data Index: 2286488 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3949. Min Range: -8.3949
Max Act: 8.0199. Min Act: -0.1700
Data Index: 8336976 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3949. Min Range: -8.3949
Max Act: 7.8949. Min Act: -0.1700
Data Index: 6991737 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3949. Min Range: -8.3949
Max Act: 7.8949. Min Act: -0.1700
Data Index: 8726236 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3949. Min Range: -8.3949
Max Act: 7.8324. Min Act: -0.1700
Data Index: 8817295 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3949. Min Range: -8.3949
Max Act: 7.7699. Min Act: -0.1700
Data Index: 7528802 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3949. Min Range: -8.3949
Max Act: 7.7074. Min Act: -0.1700
Data Index: 4559107 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3949. Min Range: -8.3949
Max Act: 7.7699. Min Act: -0.1700
Data Index: 6373058 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3949. Min Range: -8.3949
Max Act: 7.7699. Min Act: -0.1700
Data Index: 6373061 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3949. Min Range: -8.3949
Max Act: 7.7699. Min Act: -0.1700
Data Index: 5047482 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3949. Min Range: -8.3949
Max Act: 7.7074. Min Act: -0.1700
Data Index: 1138871 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3949. Min Range: -8.3949
Max Act: 7.6449. Min Act: -0.1700
Data Index: 1456822 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3949. Min Range: -8.3949
Max Act: 7.6449. Min Act: -0.1700
Data Index: 1527526 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3949. Min Range: -8.3949
Max Act: 7.6449. Min Act: -0.1700
Data Index: 7868329 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3949. Min Range: -8.3949
Max Act: 7.6449. Min Act: -0.1700
Data Index: 5698892 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3949. Min Range: -8.3949
Max Act: 7.5824. Min Act: -0.1700
Data Index: 3195777 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3949. Min Range: -8.3949
Max Act: 7.5199. Min Act: -0.1700
Data Index: 681433 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3949. Min Range: -8.3949
Max Act: 7.5824. Min Act: -0.1700
Data Index: 836094 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3949. Min Range: -8.3949
Max Act: 7.5199. Min Act: -0.1699
Data Index: 580836 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #19