Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4066 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2947. Min Range: -6.2947
Max Act: 6.2947. Min Act: -0.1700
Data Index: 8133160 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2947. Min Range: -6.2947
Max Act: 6.2634. Min Act: -0.1700
Data Index: 1329752 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2947. Min Range: -6.2947
Max Act: 6.2009. Min Act: -0.1700
Data Index: 5428904 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2947. Min Range: -6.2947
Max Act: 6.1697. Min Act: -0.1700
Data Index: 3609068 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2947. Min Range: -6.2947
Max Act: 6.2009. Min Act: -0.1700
Data Index: 654450 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2947. Min Range: -6.2947
Max Act: 6.2009. Min Act: -0.1700
Data Index: 4970948 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2947. Min Range: -6.2947
Max Act: 6.1072. Min Act: -0.1700
Data Index: 76789 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2947. Min Range: -6.2947
Max Act: 6.1072. Min Act: -0.1700
Data Index: 5285261 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2947. Min Range: -6.2947
Max Act: 6.1072. Min Act: -0.1700
Data Index: 8226132 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2947. Min Range: -6.2947
Max Act: 6.1072. Min Act: -0.1700
Data Index: 6577016 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2947. Min Range: -6.2947
Max Act: 6.0759. Min Act: -0.1700
Data Index: 3740059 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2947. Min Range: -6.2947
Max Act: 6.0447. Min Act: -0.1700
Data Index: 3269692 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2947. Min Range: -6.2947
Max Act: 6.0759. Min Act: -0.1700
Data Index: 1358318 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2947. Min Range: -6.2947
Max Act: 6.0447. Min Act: -0.1700
Data Index: 4249861 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2947. Min Range: -6.2947
Max Act: 6.0759. Min Act: -0.1700
Data Index: 1904045 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2947. Min Range: -6.2947
Max Act: 6.0447. Min Act: -0.1700
Data Index: 8631371 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2947. Min Range: -6.2947
Max Act: 6.0759. Min Act: -0.1700
Data Index: 5389246 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2947. Min Range: -6.2947
Max Act: 6.0759. Min Act: -0.1700
Data Index: 7255832 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2947. Min Range: -6.2947
Max Act: 6.0447. Min Act: -0.1700
Data Index: 199785 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2947. Min Range: -6.2947
Max Act: 6.0447. Min Act: -0.1700
Data Index: 6045959 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #19