Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5848 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0430. Min Range: -8.0430
Max Act: 8.0430. Min Act: -0.1700
Data Index: 2400902 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0430. Min Range: -8.0430
Max Act: 7.9493. Min Act: -0.1700
Data Index: 1739138 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0430. Min Range: -8.0430
Max Act: 7.7305. Min Act: -0.1700
Data Index: 8422162 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0430. Min Range: -8.0430
Max Act: 7.6680. Min Act: -0.1700
Data Index: 5246535 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0430. Min Range: -8.0430
Max Act: 7.6055. Min Act: -0.1700
Data Index: 5890270 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0430. Min Range: -8.0430
Max Act: 7.5118. Min Act: -0.1700
Data Index: 7681369 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0430. Min Range: -8.0430
Max Act: 7.5430. Min Act: -0.1700
Data Index: 785274 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0430. Min Range: -8.0430
Max Act: 7.5430. Min Act: -0.1700
Data Index: 5143041 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0430. Min Range: -8.0430
Max Act: 7.5430. Min Act: -0.1700
Data Index: 8771227 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0430. Min Range: -8.0430
Max Act: 7.5430. Min Act: -0.1700
Data Index: 2999682 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0430. Min Range: -8.0430
Max Act: 7.4805. Min Act: -0.1700
Data Index: 8782050 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0430. Min Range: -8.0430
Max Act: 7.4493. Min Act: -0.1700
Data Index: 6867309 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0430. Min Range: -8.0430
Max Act: 7.3868. Min Act: -0.1700
Data Index: 2671497 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0430. Min Range: -8.0430
Max Act: 7.2930. Min Act: -0.1700
Data Index: 6492807 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0430. Min Range: -8.0430
Max Act: 7.2930. Min Act: -0.1700
Data Index: 812380 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0430. Min Range: -8.0430
Max Act: 7.3243. Min Act: -0.1700
Data Index: 1037986 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0430. Min Range: -8.0430
Max Act: 7.2618. Min Act: -0.1700
Data Index: 5261533 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0430. Min Range: -8.0430
Max Act: 7.1680. Min Act: -0.1700
Data Index: 5300341 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0430. Min Range: -8.0430
Max Act: 7.1680. Min Act: -0.1700
Data Index: 573380 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0430. Min Range: -8.0430
Max Act: 7.1055. Min Act: -0.1700
Data Index: 28830 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19