Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5762 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8111. Min Range: -7.8111
Max Act: 7.8111. Min Act: -0.1700
Data Index: 8301391 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8111. Min Range: -7.8111
Max Act: 7.8111. Min Act: -0.1700
Data Index: 5734302 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8111. Min Range: -7.8111
Max Act: 7.7486. Min Act: -0.1700
Data Index: 7262580 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8111. Min Range: -7.8111
Max Act: 7.7486. Min Act: -0.1700
Data Index: 5960565 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8111. Min Range: -7.8111
Max Act: 7.6861. Min Act: -0.1700
Data Index: 1268003 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8111. Min Range: -7.8111
Max Act: 7.6236. Min Act: -0.1700
Data Index: 4558489 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8111. Min Range: -7.8111
Max Act: 7.5611. Min Act: -0.1700
Data Index: 483690 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8111. Min Range: -7.8111
Max Act: 7.6236. Min Act: -0.1700
Data Index: 6657906 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8111. Min Range: -7.8111
Max Act: 7.6236. Min Act: -0.1700
Data Index: 7683729 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8111. Min Range: -7.8111
Max Act: 7.5611. Min Act: -0.1700
Data Index: 3105432 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8111. Min Range: -7.8111
Max Act: 7.5611. Min Act: -0.1700
Data Index: 3419371 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8111. Min Range: -7.8111
Max Act: 7.5611. Min Act: -0.1700
Data Index: 4824550 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8111. Min Range: -7.8111
Max Act: 7.5611. Min Act: -0.1700
Data Index: 1227867 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8111. Min Range: -7.8111
Max Act: 7.5611. Min Act: -0.1700
Data Index: 2711154 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8111. Min Range: -7.8111
Max Act: 7.5298. Min Act: -0.1700
Data Index: 8765325 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8111. Min Range: -7.8111
Max Act: 7.5298. Min Act: -0.1700
Data Index: 5029384 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8111. Min Range: -7.8111
Max Act: 7.5298. Min Act: -0.1700
Data Index: 3221619 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8111. Min Range: -7.8111
Max Act: 7.4986. Min Act: -0.1700
Data Index: 3318536 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8111. Min Range: -7.8111
Max Act: 7.4673. Min Act: -0.1700
Data Index: 822202 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8111. Min Range: -7.8111
Max Act: 7.4673. Min Act: -0.1700
Data Index: 3259375 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19