Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2795 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7040. Min Range: -7.7040
Max Act: 7.7040. Min Act: -0.1700
Data Index: 1397036 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7040. Min Range: -7.7040
Max Act: 7.5478. Min Act: -0.1700
Data Index: 2966846 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7040. Min Range: -7.7040
Max Act: 7.4853. Min Act: -0.1700
Data Index: 1247507 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7040. Min Range: -7.7040
Max Act: 7.4540. Min Act: -0.1700
Data Index: 2093151 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7040. Min Range: -7.7040
Max Act: 7.2040. Min Act: -0.1700
Data Index: 5754018 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7040. Min Range: -7.7040
Max Act: 7.2040. Min Act: -0.1700
Data Index: 2544211 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7040. Min Range: -7.7040
Max Act: 7.1728. Min Act: -0.1700
Data Index: 4203490 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7040. Min Range: -7.7040
Max Act: 7.1415. Min Act: -0.1700
Data Index: 751713 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7040. Min Range: -7.7040
Max Act: 7.1103. Min Act: -0.1700
Data Index: 7301234 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7040. Min Range: -7.7040
Max Act: 7.0165. Min Act: -0.1700
Data Index: 3068886 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7040. Min Range: -7.7040
Max Act: 7.0165. Min Act: -0.1700
Data Index: 1950720 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7040. Min Range: -7.7040
Max Act: 6.9853. Min Act: -0.1700
Data Index: 6048863 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7040. Min Range: -7.7040
Max Act: 6.9540. Min Act: -0.1700
Data Index: 6104547 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7040. Min Range: -7.7040
Max Act: 6.9228. Min Act: -0.1700
Data Index: 7055132 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7040. Min Range: -7.7040
Max Act: 6.9540. Min Act: -0.1700
Data Index: 2764081 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7040. Min Range: -7.7040
Max Act: 6.9228. Min Act: -0.1700
Data Index: 5197066 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7040. Min Range: -7.7040
Max Act: 6.8915. Min Act: -0.1700
Data Index: 6901584 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7040. Min Range: -7.7040
Max Act: 6.9228. Min Act: -0.1700
Data Index: 976271 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7040. Min Range: -7.7040
Max Act: 6.8603. Min Act: -0.1700
Data Index: 5710742 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7040. Min Range: -7.7040
Max Act: 6.8915. Min Act: -0.1700
Data Index: 1623712 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19