Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2491 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4293. Min Range: -8.4293
Max Act: 8.4293. Min Act: -0.1700
Data Index: 5877608 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4293. Min Range: -8.4293
Max Act: 8.3043. Min Act: -0.1700
Data Index: 297326 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4293. Min Range: -8.4293
Max Act: 8.3043. Min Act: -0.1700
Data Index: 634766 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4293. Min Range: -8.4293
Max Act: 8.3668. Min Act: -0.1700
Data Index: 6790290 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4293. Min Range: -8.4293
Max Act: 8.2418. Min Act: -0.1700
Data Index: 8107643 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4293. Min Range: -8.4293
Max Act: 8.1793. Min Act: -0.1700
Data Index: 4419014 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4293. Min Range: -8.4293
Max Act: 8.2418. Min Act: -0.1700
Data Index: 1887450 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4293. Min Range: -8.4293
Max Act: 8.2418. Min Act: -0.1700
Data Index: 7520710 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4293. Min Range: -8.4293
Max Act: 8.1793. Min Act: -0.1700
Data Index: 2438836 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4293. Min Range: -8.4293
Max Act: 8.1793. Min Act: -0.1700
Data Index: 3116056 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4293. Min Range: -8.4293
Max Act: 8.1793. Min Act: -0.1700
Data Index: 2896581 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4293. Min Range: -8.4293
Max Act: 8.1793. Min Act: -0.1700
Data Index: 5222837 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4293. Min Range: -8.4293
Max Act: 8.1793. Min Act: -0.1700
Data Index: 5185971 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4293. Min Range: -8.4293
Max Act: 8.1793. Min Act: -0.1700
Data Index: 4989746 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4293. Min Range: -8.4293
Max Act: 8.1793. Min Act: -0.1700
Data Index: 7258180 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4293. Min Range: -8.4293
Max Act: 8.1793. Min Act: -0.1700
Data Index: 3690445 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4293. Min Range: -8.4293
Max Act: 8.1793. Min Act: -0.1700
Data Index: 6697000 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4293. Min Range: -8.4293
Max Act: 8.1793. Min Act: -0.1700
Data Index: 1213874 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4293. Min Range: -8.4293
Max Act: 8.1793. Min Act: -0.1700
Data Index: 885930 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4293. Min Range: -8.4293
Max Act: 8.1793. Min Act: -0.1700
Data Index: 5498759 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19