Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1721 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 10.1055. Min Range: -10.1055
Max Act: 10.1055. Min Act: -0.1700
Data Index: 601013 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1055. Min Range: -10.1055
Max Act: 9.8555. Min Act: -0.1700
Data Index: 3993014 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1055. Min Range: -10.1055
Max Act: 9.6055. Min Act: -0.1700
Data Index: 3965764 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1055. Min Range: -10.1055
Max Act: 9.6055. Min Act: -0.1700
Data Index: 4071445 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1055. Min Range: -10.1055
Max Act: 9.5430. Min Act: -0.1700
Data Index: 479469 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1055. Min Range: -10.1055
Max Act: 9.5430. Min Act: -0.1700
Data Index: 581011 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1055. Min Range: -10.1055
Max Act: 9.4805. Min Act: -0.1700
Data Index: 6191497 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1055. Min Range: -10.1055
Max Act: 9.4805. Min Act: -0.1700
Data Index: 220652 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1055. Min Range: -10.1055
Max Act: 9.4805. Min Act: -0.1700
Data Index: 4562949 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1055. Min Range: -10.1055
Max Act: 9.4180. Min Act: -0.1700
Data Index: 5019864 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1055. Min Range: -10.1055
Max Act: 9.4180. Min Act: -0.1700
Data Index: 5647344 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1055. Min Range: -10.1055
Max Act: 9.4180. Min Act: -0.1700
Data Index: 5993545 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1055. Min Range: -10.1055
Max Act: 9.4180. Min Act: -0.1700
Data Index: 3302014 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1055. Min Range: -10.1055
Max Act: 9.3555. Min Act: -0.1700
Data Index: 1129132 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1055. Min Range: -10.1055
Max Act: 9.3555. Min Act: -0.1700
Data Index: 5091073 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1055. Min Range: -10.1055
Max Act: 9.3555. Min Act: -0.1700
Data Index: 5647341 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1055. Min Range: -10.1055
Max Act: 9.3555. Min Act: -0.1700
Data Index: 2784714 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1055. Min Range: -10.1055
Max Act: 9.3555. Min Act: -0.1700
Data Index: 3246779 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1055. Min Range: -10.1055
Max Act: 9.3555. Min Act: -0.1700
Data Index: 4389613 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1055. Min Range: -10.1055
Max Act: 9.3555. Min Act: -0.1700
Data Index: 6681544 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #19