Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3034 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7820. Min Range: -3.7820
Max Act: 3.7820. Min Act: -0.1700
Data Index: 2994682 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7820. Min Range: -3.7820
Max Act: 3.7664. Min Act: -0.1700
Data Index: 1079864 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7820. Min Range: -3.7820
Max Act: 3.7507. Min Act: -0.1700
Data Index: 662595 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7820. Min Range: -3.7820
Max Act: 3.7507. Min Act: -0.1700
Data Index: 469722 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7820. Min Range: -3.7820
Max Act: 3.7038. Min Act: -0.1700
Data Index: 3150083 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7820. Min Range: -3.7820
Max Act: 3.6725. Min Act: -0.1700
Data Index: 79885 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7820. Min Range: -3.7820
Max Act: 3.6256. Min Act: -0.1700
Data Index: 1768836 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7820. Min Range: -3.7820
Max Act: 3.6099. Min Act: -0.1700
Data Index: 151211 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7820. Min Range: -3.7820
Max Act: 3.5786. Min Act: -0.1700
Data Index: 2815719 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7820. Min Range: -3.7820
Max Act: 3.5786. Min Act: -0.1700
Data Index: 3165432 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7820. Min Range: -3.7820
Max Act: 3.5786. Min Act: -0.1700
Data Index: 6084759 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7820. Min Range: -3.7820
Max Act: 3.5786. Min Act: -0.1700
Data Index: 4362736 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7820. Min Range: -3.7820
Max Act: 3.5786. Min Act: -0.1700
Data Index: 1654956 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7820. Min Range: -3.7820
Max Act: 3.5630. Min Act: -0.1700
Data Index: 6440301 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7820. Min Range: -3.7820
Max Act: 3.5630. Min Act: -0.1700
Data Index: 3390372 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7820. Min Range: -3.7820
Max Act: 3.5630. Min Act: -0.1700
Data Index: 509088 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7820. Min Range: -3.7820
Max Act: 3.5473. Min Act: -0.1700
Data Index: 3236381 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7820. Min Range: -3.7820
Max Act: 3.5316. Min Act: -0.1700
Data Index: 6676834 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7820. Min Range: -3.7820
Max Act: 3.5316. Min Act: -0.1700
Data Index: 4253387 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7820. Min Range: -3.7820
Max Act: 3.5160. Min Act: -0.1700
Data Index: 6005262 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #19