Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4816 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1193. Min Range: -7.1193
Max Act: 7.1193. Min Act: -0.1700
Data Index: 8357913 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1193. Min Range: -7.1193
Max Act: 6.9005. Min Act: -0.1700
Data Index: 4132537 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1193. Min Range: -7.1193
Max Act: 6.8693. Min Act: -0.1700
Data Index: 7315312 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1193. Min Range: -7.1193
Max Act: 6.8380. Min Act: -0.1700
Data Index: 6069480 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1193. Min Range: -7.1193
Max Act: 6.7755. Min Act: -0.1700
Data Index: 2769590 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1193. Min Range: -7.1193
Max Act: 6.6818. Min Act: -0.1700
Data Index: 5414617 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1193. Min Range: -7.1193
Max Act: 6.7130. Min Act: -0.1700
Data Index: 8037441 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1193. Min Range: -7.1193
Max Act: 6.6193. Min Act: -0.1700
Data Index: 7950479 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1193. Min Range: -7.1193
Max Act: 6.6193. Min Act: -0.1700
Data Index: 3288758 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1193. Min Range: -7.1193
Max Act: 6.5568. Min Act: -0.1700
Data Index: 969933 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1193. Min Range: -7.1193
Max Act: 6.5568. Min Act: -0.1700
Data Index: 7124957 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1193. Min Range: -7.1193
Max Act: 6.5568. Min Act: -0.1700
Data Index: 829631 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1193. Min Range: -7.1193
Max Act: 6.4943. Min Act: -0.1700
Data Index: 4814409 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1193. Min Range: -7.1193
Max Act: 6.4943. Min Act: -0.1700
Data Index: 7408979 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1193. Min Range: -7.1193
Max Act: 6.4318. Min Act: -0.1700
Data Index: 3501794 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1193. Min Range: -7.1193
Max Act: 6.4005. Min Act: -0.1700
Data Index: 3425995 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1193. Min Range: -7.1193
Max Act: 6.4005. Min Act: -0.1700
Data Index: 3399132 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1193. Min Range: -7.1193
Max Act: 6.4318. Min Act: -0.1700
Data Index: 1813966 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1193. Min Range: -7.1193
Max Act: 6.4318. Min Act: -0.1700
Data Index: 5325846 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1193. Min Range: -7.1193
Max Act: 6.3693. Min Act: -0.1700
Data Index: 5302344 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19