Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1593 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7328. Min Range: -5.7328
Max Act: 5.7328. Min Act: -0.1700
Data Index: 6114219 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7328. Min Range: -5.7328
Max Act: 5.6703. Min Act: -0.1700
Data Index: 8767663 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7328. Min Range: -5.7328
Max Act: 5.4515. Min Act: -0.1700
Data Index: 1066425 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7328. Min Range: -5.7328
Max Act: 5.4828. Min Act: -0.1700
Data Index: 6114221 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7328. Min Range: -5.7328
Max Act: 5.3265. Min Act: -0.1700
Data Index: 937466 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7328. Min Range: -5.7328
Max Act: 5.2953. Min Act: -0.1700
Data Index: 6883169 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7328. Min Range: -5.7328
Max Act: 5.3578. Min Act: -0.1700
Data Index: 6759845 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7328. Min Range: -5.7328
Max Act: 5.3265. Min Act: -0.1700
Data Index: 229093 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7328. Min Range: -5.7328
Max Act: 5.2953. Min Act: -0.1700
Data Index: 1830566 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7328. Min Range: -5.7328
Max Act: 5.2640. Min Act: -0.1700
Data Index: 2362053 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7328. Min Range: -5.7328
Max Act: 5.2328. Min Act: -0.1700
Data Index: 7254178 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7328. Min Range: -5.7328
Max Act: 5.2015. Min Act: -0.1700
Data Index: 5500029 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7328. Min Range: -5.7328
Max Act: 5.2015. Min Act: -0.1700
Data Index: 1316016 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7328. Min Range: -5.7328
Max Act: 5.2328. Min Act: -0.1700
Data Index: 2634351 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7328. Min Range: -5.7328
Max Act: 5.2015. Min Act: -0.1700
Data Index: 3439258 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7328. Min Range: -5.7328
Max Act: 5.2328. Min Act: -0.1700
Data Index: 4342141 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7328. Min Range: -5.7328
Max Act: 5.1703. Min Act: -0.1700
Data Index: 2073037 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7328. Min Range: -5.7328
Max Act: 5.1703. Min Act: -0.1700
Data Index: 7303737 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7328. Min Range: -5.7328
Max Act: 5.1390. Min Act: -0.1700
Data Index: 1451763 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7328. Min Range: -5.7328
Max Act: 5.1390. Min Act: -0.1700
Data Index: 7467783 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #19