Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 513 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8742. Min Range: -6.8742
Max Act: 6.8742. Min Act: -0.1700
Data Index: 7374270 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8742. Min Range: -6.8742
Max Act: 6.7492. Min Act: -0.1700
Data Index: 6905580 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8742. Min Range: -6.8742
Max Act: 6.7179. Min Act: -0.1700
Data Index: 1462913 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8742. Min Range: -6.8742
Max Act: 6.6554. Min Act: -0.1700
Data Index: 3940373 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8742. Min Range: -6.8742
Max Act: 6.6554. Min Act: -0.1700
Data Index: 69827 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8742. Min Range: -6.8742
Max Act: 6.5617. Min Act: -0.1700
Data Index: 4229463 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8742. Min Range: -6.8742
Max Act: 6.5929. Min Act: -0.1700
Data Index: 4749253 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8742. Min Range: -6.8742
Max Act: 6.5304. Min Act: -0.1700
Data Index: 4259925 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8742. Min Range: -6.8742
Max Act: 6.4992. Min Act: -0.1700
Data Index: 1128060 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8742. Min Range: -6.8742
Max Act: 6.4992. Min Act: -0.1700
Data Index: 3794792 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8742. Min Range: -6.8742
Max Act: 6.4992. Min Act: -0.1700
Data Index: 1842951 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8742. Min Range: -6.8742
Max Act: 6.4992. Min Act: -0.1700
Data Index: 2194975 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8742. Min Range: -6.8742
Max Act: 6.4992. Min Act: -0.1700
Data Index: 542147 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8742. Min Range: -6.8742
Max Act: 6.4679. Min Act: -0.1700
Data Index: 2517542 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8742. Min Range: -6.8742
Max Act: 6.4679. Min Act: -0.1700
Data Index: 8273744 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8742. Min Range: -6.8742
Max Act: 6.4679. Min Act: -0.1700
Data Index: 6700468 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8742. Min Range: -6.8742
Max Act: 6.4679. Min Act: -0.1700
Data Index: 53557 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8742. Min Range: -6.8742
Max Act: 6.4679. Min Act: -0.1700
Data Index: 6370415 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8742. Min Range: -6.8742
Max Act: 6.4679. Min Act: -0.1700
Data Index: 1103487 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8742. Min Range: -6.8742
Max Act: 6.4054. Min Act: -0.1700
Data Index: 6627220 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19