Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1496 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7095. Min Range: -4.7095
Max Act: 4.7095. Min Act: -0.1700
Data Index: 687648 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7095. Min Range: -4.7095
Max Act: 4.5845. Min Act: -0.1700
Data Index: 1360342 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7095. Min Range: -4.7095
Max Act: 4.5845. Min Act: -0.1700
Data Index: 7269910 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7095. Min Range: -4.7095
Max Act: 4.5845. Min Act: -0.1700
Data Index: 1052296 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7095. Min Range: -4.7095
Max Act: 4.5845. Min Act: -0.1700
Data Index: 6048396 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7095. Min Range: -4.7095
Max Act: 4.5532. Min Act: -0.1700
Data Index: 6419903 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7095. Min Range: -4.7095
Max Act: 4.5532. Min Act: -0.1700
Data Index: 492031 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7095. Min Range: -4.7095
Max Act: 4.5220. Min Act: -0.1700
Data Index: 4057119 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7095. Min Range: -4.7095
Max Act: 4.5220. Min Act: -0.1700
Data Index: 499370 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7095. Min Range: -4.7095
Max Act: 4.5220. Min Act: -0.1700
Data Index: 766358 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7095. Min Range: -4.7095
Max Act: 4.4907. Min Act: -0.1700
Data Index: 1736376 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7095. Min Range: -4.7095
Max Act: 4.4907. Min Act: -0.1700
Data Index: 8406798 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7095. Min Range: -4.7095
Max Act: 4.4907. Min Act: -0.1700
Data Index: 7634769 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7095. Min Range: -4.7095
Max Act: 4.4595. Min Act: -0.1700
Data Index: 2066777 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7095. Min Range: -4.7095
Max Act: 4.4282. Min Act: -0.1700
Data Index: 2917014 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7095. Min Range: -4.7095
Max Act: 4.4282. Min Act: -0.1700
Data Index: 243945 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7095. Min Range: -4.7095
Max Act: 4.4282. Min Act: -0.1700
Data Index: 7463260 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7095. Min Range: -4.7095
Max Act: 4.4282. Min Act: -0.1700
Data Index: 4991288 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7095. Min Range: -4.7095
Max Act: 4.4282. Min Act: -0.1700
Data Index: 6516851 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7095. Min Range: -4.7095
Max Act: 4.4282. Min Act: -0.1700
Data Index: 6209486 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19