Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5444 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6806. Min Range: -5.6806
Max Act: 5.6806. Min Act: -0.1700
Data Index: 4371715 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6806. Min Range: -5.6806
Max Act: 5.6181. Min Act: -0.1700
Data Index: 3645881 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6806. Min Range: -5.6806
Max Act: 5.6181. Min Act: -0.1700
Data Index: 2213719 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6806. Min Range: -5.6806
Max Act: 5.6181. Min Act: -0.1700
Data Index: 6478133 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6806. Min Range: -5.6806
Max Act: 5.5243. Min Act: -0.1700
Data Index: 3058358 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6806. Min Range: -5.6806
Max Act: 5.5243. Min Act: -0.1700
Data Index: 3634975 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6806. Min Range: -5.6806
Max Act: 5.5243. Min Act: -0.1700
Data Index: 5863714 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6806. Min Range: -5.6806
Max Act: 5.4931. Min Act: -0.1700
Data Index: 1380858 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6806. Min Range: -5.6806
Max Act: 5.4931. Min Act: -0.1700
Data Index: 640487 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6806. Min Range: -5.6806
Max Act: 5.4618. Min Act: -0.1700
Data Index: 7536125 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6806. Min Range: -5.6806
Max Act: 5.4618. Min Act: -0.1700
Data Index: 1603516 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6806. Min Range: -5.6806
Max Act: 5.4618. Min Act: -0.1700
Data Index: 4472296 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6806. Min Range: -5.6806
Max Act: 5.3993. Min Act: -0.1700
Data Index: 710054 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6806. Min Range: -5.6806
Max Act: 5.3993. Min Act: -0.1700
Data Index: 3643191 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6806. Min Range: -5.6806
Max Act: 5.3993. Min Act: -0.1700
Data Index: 3605157 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6806. Min Range: -5.6806
Max Act: 5.3681. Min Act: -0.1700
Data Index: 2940223 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6806. Min Range: -5.6806
Max Act: 5.3681. Min Act: -0.1700
Data Index: 7615127 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6806. Min Range: -5.6806
Max Act: 5.3681. Min Act: -0.1700
Data Index: 2257069 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6806. Min Range: -5.6806
Max Act: 5.3368. Min Act: -0.1700
Data Index: 4923475 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6806. Min Range: -5.6806
Max Act: 5.3056. Min Act: -0.1700
Data Index: 747248 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #19