Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2407 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2267. Min Range: -8.2267
Max Act: 8.2267. Min Act: -0.1700
Data Index: 1411713 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2267. Min Range: -8.2267
Max Act: 8.1955. Min Act: -0.1700
Data Index: 8147848 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2267. Min Range: -8.2267
Max Act: 8.1330. Min Act: -0.1700
Data Index: 4008334 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2267. Min Range: -8.2267
Max Act: 8.0080. Min Act: -0.1700
Data Index: 2796736 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2267. Min Range: -8.2267
Max Act: 7.9142. Min Act: -0.1700
Data Index: 4008335 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2267. Min Range: -8.2267
Max Act: 7.8517. Min Act: -0.1700
Data Index: 7114328 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2267. Min Range: -8.2267
Max Act: 7.8205. Min Act: -0.1700
Data Index: 1414334 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2267. Min Range: -8.2267
Max Act: 7.8205. Min Act: -0.1700
Data Index: 7356308 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2267. Min Range: -8.2267
Max Act: 7.7580. Min Act: -0.1700
Data Index: 1833784 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2267. Min Range: -8.2267
Max Act: 7.7892. Min Act: -0.1700
Data Index: 3571505 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2267. Min Range: -8.2267
Max Act: 7.7580. Min Act: -0.1700
Data Index: 1565227 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2267. Min Range: -8.2267
Max Act: 7.7580. Min Act: -0.1700
Data Index: 8339016 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2267. Min Range: -8.2267
Max Act: 7.6955. Min Act: -0.1700
Data Index: 1995114 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2267. Min Range: -8.2267
Max Act: 7.6642. Min Act: -0.1700
Data Index: 4210784 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2267. Min Range: -8.2267
Max Act: 7.6017. Min Act: -0.1700
Data Index: 1667673 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2267. Min Range: -8.2267
Max Act: 7.6642. Min Act: -0.1700
Data Index: 5595490 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2267. Min Range: -8.2267
Max Act: 7.6017. Min Act: -0.1700
Data Index: 1517137 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2267. Min Range: -8.2267
Max Act: 7.6330. Min Act: -0.1700
Data Index: 3386061 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2267. Min Range: -8.2267
Max Act: 7.6017. Min Act: -0.1700
Data Index: 3911406 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2267. Min Range: -8.2267
Max Act: 7.5705. Min Act: -0.1700
Data Index: 3647617 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #19