Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2751 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0929. Min Range: -9.0929
Max Act: 9.0929. Min Act: -0.1700
Data Index: 8650161 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0929. Min Range: -9.0929
Max Act: 8.9054. Min Act: -0.1700
Data Index: 4067321 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0929. Min Range: -9.0929
Max Act: 8.7179. Min Act: -0.1700
Data Index: 1851854 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0929. Min Range: -9.0929
Max Act: 8.6554. Min Act: -0.1700
Data Index: 1229247 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0929. Min Range: -9.0929
Max Act: 8.6554. Min Act: -0.1700
Data Index: 8772971 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0929. Min Range: -9.0929
Max Act: 8.5304. Min Act: -0.1700
Data Index: 5053037 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0929. Min Range: -9.0929
Max Act: 8.5929. Min Act: -0.1700
Data Index: 279959 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0929. Min Range: -9.0929
Max Act: 8.4054. Min Act: -0.1700
Data Index: 3216354 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0929. Min Range: -9.0929
Max Act: 8.4679. Min Act: -0.1700
Data Index: 6166793 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0929. Min Range: -9.0929
Max Act: 8.4679. Min Act: -0.1700
Data Index: 5921790 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0929. Min Range: -9.0929
Max Act: 8.4054. Min Act: -0.1700
Data Index: 1790159 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0929. Min Range: -9.0929
Max Act: 8.4054. Min Act: -0.1700
Data Index: 5126898 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0929. Min Range: -9.0929
Max Act: 8.4054. Min Act: -0.1700
Data Index: 5596783 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0929. Min Range: -9.0929
Max Act: 8.4054. Min Act: -0.1700
Data Index: 5419565 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0929. Min Range: -9.0929
Max Act: 8.4054. Min Act: -0.1700
Data Index: 4166723 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0929. Min Range: -9.0929
Max Act: 8.4054. Min Act: -0.1700
Data Index: 3103013 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0929. Min Range: -9.0929
Max Act: 8.2804. Min Act: -0.1700
Data Index: 4679997 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0929. Min Range: -9.0929
Max Act: 8.2804. Min Act: -0.1700
Data Index: 6242760 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0929. Min Range: -9.0929
Max Act: 8.2804. Min Act: -0.1700
Data Index: 7413158 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0929. Min Range: -9.0929
Max Act: 8.2804. Min Act: -0.1700
Data Index: 249297 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #19