Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2164 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0292. Min Range: -4.0292
Max Act: 4.0292. Min Act: -0.1700
Data Index: 606365 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0292. Min Range: -4.0292
Max Act: 3.9667. Min Act: -0.1700
Data Index: 8627330 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0292. Min Range: -4.0292
Max Act: 3.9041. Min Act: -0.1700
Data Index: 2247081 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0292. Min Range: -4.0292
Max Act: 3.8416. Min Act: -0.1700
Data Index: 2125500 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0292. Min Range: -4.0292
Max Act: 3.8729. Min Act: -0.1700
Data Index: 8092600 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0292. Min Range: -4.0292
Max Act: 3.8416. Min Act: -0.1700
Data Index: 3602710 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0292. Min Range: -4.0292
Max Act: 3.8729. Min Act: -0.1700
Data Index: 7651150 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0292. Min Range: -4.0292
Max Act: 3.8416. Min Act: -0.1700
Data Index: 703010 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0292. Min Range: -4.0292
Max Act: 3.8103. Min Act: -0.1700
Data Index: 157038 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0292. Min Range: -4.0292
Max Act: 3.8103. Min Act: -0.1700
Data Index: 781194 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0292. Min Range: -4.0292
Max Act: 3.8103. Min Act: -0.1700
Data Index: 7370753 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0292. Min Range: -4.0292
Max Act: 3.7791. Min Act: -0.1700
Data Index: 6763398 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0292. Min Range: -4.0292
Max Act: 3.8103. Min Act: -0.1700
Data Index: 789051 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0292. Min Range: -4.0292
Max Act: 3.7791. Min Act: -0.1700
Data Index: 1539581 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0292. Min Range: -4.0292
Max Act: 3.7478. Min Act: -0.1700
Data Index: 8105486 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0292. Min Range: -4.0292
Max Act: 3.7791. Min Act: -0.1700
Data Index: 3470596 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0292. Min Range: -4.0292
Max Act: 3.7791. Min Act: -0.1700
Data Index: 991103 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0292. Min Range: -4.0292
Max Act: 3.7791. Min Act: -0.1700
Data Index: 8782452 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0292. Min Range: -4.0292
Max Act: 3.7478. Min Act: -0.1700
Data Index: 1437299 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0292. Min Range: -4.0292
Max Act: 3.7165. Min Act: -0.1700
Data Index: 4542140 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #19