Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1400 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1212. Min Range: -10.1212
Max Act: 10.1212. Min Act: -0.1700
Data Index: 8494094 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1212. Min Range: -10.1212
Max Act: 8.9337. Min Act: -0.1700
Data Index: 1884853 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1212. Min Range: -10.1212
Max Act: 8.8712. Min Act: -0.1700
Data Index: 5964223 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1212. Min Range: -10.1212
Max Act: 8.7462. Min Act: -0.1700
Data Index: 1997130 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1212. Min Range: -10.1212
Max Act: 8.6837. Min Act: -0.1700
Data Index: 4616513 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1212. Min Range: -10.1212
Max Act: 8.6212. Min Act: -0.1700
Data Index: 5419878 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1212. Min Range: -10.1212
Max Act: 8.6212. Min Act: -0.1700
Data Index: 7284676 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1212. Min Range: -10.1212
Max Act: 8.5587. Min Act: -0.1700
Data Index: 4807759 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1212. Min Range: -10.1212
Max Act: 8.5587. Min Act: -0.1700
Data Index: 2977107 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1212. Min Range: -10.1212
Max Act: 8.5587. Min Act: -0.1700
Data Index: 6797756 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1212. Min Range: -10.1212
Max Act: 8.4962. Min Act: -0.1700
Data Index: 7145423 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1212. Min Range: -10.1212
Max Act: 8.4337. Min Act: -0.1700
Data Index: 7973871 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1212. Min Range: -10.1212
Max Act: 8.4337. Min Act: -0.1700
Data Index: 5703734 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1212. Min Range: -10.1212
Max Act: 8.3712. Min Act: -0.1700
Data Index: 7806115 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1212. Min Range: -10.1212
Max Act: 8.3712. Min Act: -0.1700
Data Index: 5915250 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1212. Min Range: -10.1212
Max Act: 8.3087. Min Act: -0.1700
Data Index: 5615509 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1212. Min Range: -10.1212
Max Act: 8.2462. Min Act: -0.1700
Data Index: 3649158 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1212. Min Range: -10.1212
Max Act: 8.2462. Min Act: -0.1700
Data Index: 3837318 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1212. Min Range: -10.1212
Max Act: 8.2462. Min Act: -0.1700
Data Index: 6073060 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1212. Min Range: -10.1212
Max Act: 8.1837. Min Act: -0.1700
Data Index: 1379938 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19