Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 587 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.2698. Min Range: -5.2698
Max Act: 5.2698. Min Act: -0.1700
Data Index: 5414241 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2698. Min Range: -5.2698
Max Act: 5.0198. Min Act: -0.1700
Data Index: 3907741 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2698. Min Range: -5.2698
Max Act: 5.0198. Min Act: -0.1700
Data Index: 3185180 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2698. Min Range: -5.2698
Max Act: 4.9885. Min Act: -0.1700
Data Index: 99873 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2698. Min Range: -5.2698
Max Act: 4.9260. Min Act: -0.1700
Data Index: 7017682 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2698. Min Range: -5.2698
Max Act: 4.8948. Min Act: -0.1700
Data Index: 6440251 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2698. Min Range: -5.2698
Max Act: 4.9573. Min Act: -0.1700
Data Index: 2253074 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2698. Min Range: -5.2698
Max Act: 4.8948. Min Act: -0.1700
Data Index: 2962280 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2698. Min Range: -5.2698
Max Act: 4.8635. Min Act: -0.1700
Data Index: 4149812 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2698. Min Range: -5.2698
Max Act: 4.8635. Min Act: -0.1700
Data Index: 2893374 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2698. Min Range: -5.2698
Max Act: 4.8635. Min Act: -0.1700
Data Index: 1029499 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2698. Min Range: -5.2698
Max Act: 4.8635. Min Act: -0.1700
Data Index: 1672968 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2698. Min Range: -5.2698
Max Act: 4.8635. Min Act: -0.1700
Data Index: 8381460 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2698. Min Range: -5.2698
Max Act: 4.8010. Min Act: -0.1700
Data Index: 2693126 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2698. Min Range: -5.2698
Max Act: 4.8010. Min Act: -0.1700
Data Index: 500244 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2698. Min Range: -5.2698
Max Act: 4.8010. Min Act: -0.1700
Data Index: 577234 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2698. Min Range: -5.2698
Max Act: 4.7698. Min Act: -0.1700
Data Index: 4690125 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2698. Min Range: -5.2698
Max Act: 4.7698. Min Act: -0.1700
Data Index: 3782956 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2698. Min Range: -5.2698
Max Act: 4.7698. Min Act: -0.1700
Data Index: 535159 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2698. Min Range: -5.2698
Max Act: 4.7698. Min Act: -0.1700
Data Index: 223601 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19