Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3472 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9196. Min Range: -6.9196
Max Act: 6.9196. Min Act: -0.1700
Data Index: 7064120 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9196. Min Range: -6.9196
Max Act: 6.6383. Min Act: -0.1700
Data Index: 4251806 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9196. Min Range: -6.9196
Max Act: 6.6071. Min Act: -0.1700
Data Index: 1834183 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9196. Min Range: -6.9196
Max Act: 6.5758. Min Act: -0.1700
Data Index: 5381170 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9196. Min Range: -6.9196
Max Act: 6.6071. Min Act: -0.1700
Data Index: 4781355 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9196. Min Range: -6.9196
Max Act: 6.5758. Min Act: -0.1700
Data Index: 2034326 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9196. Min Range: -6.9196
Max Act: 6.5446. Min Act: -0.1700
Data Index: 3315814 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9196. Min Range: -6.9196
Max Act: 6.5446. Min Act: -0.1700
Data Index: 939868 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9196. Min Range: -6.9196
Max Act: 6.5133. Min Act: -0.1700
Data Index: 7761675 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9196. Min Range: -6.9196
Max Act: 6.3571. Min Act: -0.1700
Data Index: 4054141 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9196. Min Range: -6.9196
Max Act: 6.3258. Min Act: -0.1700
Data Index: 2077256 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9196. Min Range: -6.9196
Max Act: 6.2946. Min Act: -0.1700
Data Index: 6701011 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9196. Min Range: -6.9196
Max Act: 6.2946. Min Act: -0.1700
Data Index: 8659765 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9196. Min Range: -6.9196
Max Act: 6.2633. Min Act: -0.1700
Data Index: 1257297 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9196. Min Range: -6.9196
Max Act: 6.2633. Min Act: -0.1700
Data Index: 8111199 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9196. Min Range: -6.9196
Max Act: 6.2633. Min Act: -0.1700
Data Index: 6246545 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9196. Min Range: -6.9196
Max Act: 6.2008. Min Act: -0.1700
Data Index: 2544671 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9196. Min Range: -6.9196
Max Act: 6.2321. Min Act: -0.1700
Data Index: 2965954 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9196. Min Range: -6.9196
Max Act: 6.1696. Min Act: -0.1700
Data Index: 2116356 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9196. Min Range: -6.9196
Max Act: 6.1383. Min Act: -0.1700
Data Index: 7073389 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19