Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2437 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7298. Min Range: -7.7298
Max Act: 7.7298. Min Act: -0.1700
Data Index: 1409829 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7298. Min Range: -7.7298
Max Act: 7.6048. Min Act: -0.1700
Data Index: 3534132 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7298. Min Range: -7.7298
Max Act: 7.3861. Min Act: -0.1700
Data Index: 5157587 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7298. Min Range: -7.7298
Max Act: 7.3548. Min Act: -0.1700
Data Index: 8361651 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7298. Min Range: -7.7298
Max Act: 7.3236. Min Act: -0.1700
Data Index: 2112487 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7298. Min Range: -7.7298
Max Act: 7.2923. Min Act: -0.1700
Data Index: 8221641 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7298. Min Range: -7.7298
Max Act: 7.2298. Min Act: -0.1700
Data Index: 5703 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7298. Min Range: -7.7298
Max Act: 7.2298. Min Act: -0.1700
Data Index: 7030951 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7298. Min Range: -7.7298
Max Act: 7.1986. Min Act: -0.1700
Data Index: 5345421 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7298. Min Range: -7.7298
Max Act: 7.1986. Min Act: -0.1700
Data Index: 8053523 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7298. Min Range: -7.7298
Max Act: 7.1986. Min Act: -0.1700
Data Index: 5070561 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7298. Min Range: -7.7298
Max Act: 7.1673. Min Act: -0.1700
Data Index: 4186311 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7298. Min Range: -7.7298
Max Act: 7.1048. Min Act: -0.1700
Data Index: 1968930 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7298. Min Range: -7.7298
Max Act: 7.1361. Min Act: -0.1700
Data Index: 7256717 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7298. Min Range: -7.7298
Max Act: 7.1361. Min Act: -0.1700
Data Index: 8350329 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7298. Min Range: -7.7298
Max Act: 7.0736. Min Act: -0.1700
Data Index: 5816974 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7298. Min Range: -7.7298
Max Act: 7.1048. Min Act: -0.1700
Data Index: 7376765 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7298. Min Range: -7.7298
Max Act: 7.1048. Min Act: -0.1700
Data Index: 7958275 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7298. Min Range: -7.7298
Max Act: 7.0423. Min Act: -0.1700
Data Index: 7336837 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7298. Min Range: -7.7298
Max Act: 7.0111. Min Act: -0.1700
Data Index: 691255 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #19