Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3041 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.9571. Min Range: -7.9571
Max Act: 7.9571. Min Act: -0.1700
Data Index: 7767496 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9571. Min Range: -7.9571
Max Act: 7.9571. Min Act: -0.1700
Data Index: 2982369 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9571. Min Range: -7.9571
Max Act: 7.8634. Min Act: -0.1700
Data Index: 4137056 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9571. Min Range: -7.9571
Max Act: 7.6134. Min Act: -0.1700
Data Index: 2718697 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9571. Min Range: -7.9571
Max Act: 7.5509. Min Act: -0.1700
Data Index: 434165 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9571. Min Range: -7.9571
Max Act: 7.4884. Min Act: -0.1700
Data Index: 5256631 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9571. Min Range: -7.9571
Max Act: 7.4259. Min Act: -0.1700
Data Index: 5740519 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9571. Min Range: -7.9571
Max Act: 7.3321. Min Act: -0.1700
Data Index: 1130541 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9571. Min Range: -7.9571
Max Act: 7.3634. Min Act: -0.1700
Data Index: 1080745 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9571. Min Range: -7.9571
Max Act: 7.3321. Min Act: -0.1700
Data Index: 6217505 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9571. Min Range: -7.9571
Max Act: 7.3321. Min Act: -0.1700
Data Index: 3066414 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9571. Min Range: -7.9571
Max Act: 7.3321. Min Act: -0.1700
Data Index: 6117097 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9571. Min Range: -7.9571
Max Act: 7.3009. Min Act: -0.1700
Data Index: 622031 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9571. Min Range: -7.9571
Max Act: 7.3321. Min Act: -0.1700
Data Index: 5163787 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9571. Min Range: -7.9571
Max Act: 7.3321. Min Act: -0.1700
Data Index: 869321 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9571. Min Range: -7.9571
Max Act: 7.2696. Min Act: -0.1700
Data Index: 5987904 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9571. Min Range: -7.9571
Max Act: 7.3009. Min Act: -0.1700
Data Index: 1761362 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9571. Min Range: -7.9571
Max Act: 7.2384. Min Act: -0.1700
Data Index: 6066266 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9571. Min Range: -7.9571
Max Act: 7.2696. Min Act: -0.1700
Data Index: 4945853 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9571. Min Range: -7.9571
Max Act: 7.1759. Min Act: -0.1700
Data Index: 7480761 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19