Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 726 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7924. Min Range: -4.7924
Max Act: 4.7611. Min Act: -0.1700
Data Index: 7952645 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7924. Min Range: -4.7924
Max Act: 4.7924. Min Act: -0.1700
Data Index: 1001041 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7924. Min Range: -4.7924
Max Act: 4.4799. Min Act: -0.1700
Data Index: 4169170 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7924. Min Range: -4.7924
Max Act: 4.4486. Min Act: -0.1700
Data Index: 1794737 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7924. Min Range: -4.7924
Max Act: 4.3861. Min Act: -0.1700
Data Index: 7271512 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7924. Min Range: -4.7924
Max Act: 4.3236. Min Act: -0.1700
Data Index: 7194850 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7924. Min Range: -4.7924
Max Act: 4.2298. Min Act: -0.1700
Data Index: 739925 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7924. Min Range: -4.7924
Max Act: 4.2923. Min Act: -0.1700
Data Index: 6010131 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7924. Min Range: -4.7924
Max Act: 4.2923. Min Act: -0.1700
Data Index: 7328200 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7924. Min Range: -4.7924
Max Act: 4.2923. Min Act: -0.1700
Data Index: 2078589 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7924. Min Range: -4.7924
Max Act: 4.2298. Min Act: -0.1700
Data Index: 2737558 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7924. Min Range: -4.7924
Max Act: 4.3548. Min Act: -0.1700
Data Index: 293700 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7924. Min Range: -4.7924
Max Act: 4.3236. Min Act: -0.1700
Data Index: 200713 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7924. Min Range: -4.7924
Max Act: 4.2923. Min Act: -0.1700
Data Index: 8804636 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7924. Min Range: -4.7924
Max Act: 4.2923. Min Act: -0.1700
Data Index: 297186 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7924. Min Range: -4.7924
Max Act: 4.3236. Min Act: -0.1700
Data Index: 7338267 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7924. Min Range: -4.7924
Max Act: 4.2923. Min Act: -0.1700
Data Index: 5186471 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7924. Min Range: -4.7924
Max Act: 4.2298. Min Act: -0.1700
Data Index: 414790 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7924. Min Range: -4.7924
Max Act: 4.2923. Min Act: -0.1700
Data Index: 7513479 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7924. Min Range: -4.7924
Max Act: 4.2923. Min Act: -0.1700
Data Index: 6294524 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #19