Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1512 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0282. Min Range: -8.0282
Max Act: 8.0282. Min Act: -0.1700
Data Index: 2451635 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0282. Min Range: -8.0282
Max Act: 7.1220. Min Act: -0.1700
Data Index: 340586 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0282. Min Range: -8.0282
Max Act: 7.1220. Min Act: -0.1700
Data Index: 373867 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0282. Min Range: -8.0282
Max Act: 6.9970. Min Act: -0.1700
Data Index: 1315495 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0282. Min Range: -8.0282
Max Act: 6.9657. Min Act: -0.1700
Data Index: 3186317 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0282. Min Range: -8.0282
Max Act: 6.9657. Min Act: -0.1700
Data Index: 8102417 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0282. Min Range: -8.0282
Max Act: 6.9345. Min Act: -0.1700
Data Index: 1345775 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0282. Min Range: -8.0282
Max Act: 6.9032. Min Act: -0.1700
Data Index: 8333235 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0282. Min Range: -8.0282
Max Act: 6.8720. Min Act: -0.1700
Data Index: 7759371 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0282. Min Range: -8.0282
Max Act: 6.9032. Min Act: -0.1700
Data Index: 1916030 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0282. Min Range: -8.0282
Max Act: 6.9345. Min Act: -0.1700
Data Index: 2937580 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0282. Min Range: -8.0282
Max Act: 6.8720. Min Act: -0.1700
Data Index: 2209711 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0282. Min Range: -8.0282
Max Act: 6.8720. Min Act: -0.1700
Data Index: 677823 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0282. Min Range: -8.0282
Max Act: 6.8095. Min Act: -0.1700
Data Index: 5020788 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0282. Min Range: -8.0282
Max Act: 6.8407. Min Act: -0.1700
Data Index: 6266495 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0282. Min Range: -8.0282
Max Act: 6.8407. Min Act: -0.1700
Data Index: 3868974 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0282. Min Range: -8.0282
Max Act: 6.7782. Min Act: -0.1700
Data Index: 1458553 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0282. Min Range: -8.0282
Max Act: 6.8095. Min Act: -0.1700
Data Index: 6719521 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0282. Min Range: -8.0282
Max Act: 6.7782. Min Act: -0.1700
Data Index: 6518765 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0282. Min Range: -8.0282
Max Act: 6.8095. Min Act: -0.1700
Data Index: 3396106 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19