Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1642 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1799. Min Range: -5.1799
Max Act: 5.1799. Min Act: -0.1700
Data Index: 209682 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1799. Min Range: -5.1799
Max Act: 5.0861. Min Act: -0.1700
Data Index: 559101 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1799. Min Range: -5.1799
Max Act: 4.9924. Min Act: -0.1700
Data Index: 4237583 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1799. Min Range: -5.1799
Max Act: 4.9924. Min Act: -0.1700
Data Index: 3806044 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1799. Min Range: -5.1799
Max Act: 4.9924. Min Act: -0.1700
Data Index: 7028610 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1799. Min Range: -5.1799
Max Act: 4.9924. Min Act: -0.1700
Data Index: 7108367 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1799. Min Range: -5.1799
Max Act: 4.9299. Min Act: -0.1700
Data Index: 5227941 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1799. Min Range: -5.1799
Max Act: 4.9611. Min Act: -0.1700
Data Index: 5360393 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1799. Min Range: -5.1799
Max Act: 4.9611. Min Act: -0.1700
Data Index: 2543707 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1799. Min Range: -5.1799
Max Act: 4.9924. Min Act: -0.1700
Data Index: 4555999 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1799. Min Range: -5.1799
Max Act: 4.9611. Min Act: -0.1700
Data Index: 7029098 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1799. Min Range: -5.1799
Max Act: 4.9299. Min Act: -0.1700
Data Index: 2855348 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1799. Min Range: -5.1799
Max Act: 4.9299. Min Act: -0.1700
Data Index: 4464250 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1799. Min Range: -5.1799
Max Act: 4.9299. Min Act: -0.1700
Data Index: 788961 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1799. Min Range: -5.1799
Max Act: 4.9299. Min Act: -0.1700
Data Index: 4688976 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1799. Min Range: -5.1799
Max Act: 4.8986. Min Act: -0.1700
Data Index: 1223654 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1799. Min Range: -5.1799
Max Act: 4.9299. Min Act: -0.1700
Data Index: 2083498 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1799. Min Range: -5.1799
Max Act: 4.9299. Min Act: -0.1700
Data Index: 6903507 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1799. Min Range: -5.1799
Max Act: 4.8986. Min Act: -0.1700
Data Index: 5367480 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1799. Min Range: -5.1799
Max Act: 4.8986. Min Act: -0.1700
Data Index: 6186147 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19