Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4635 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.3405. Min Act: -0.1700
Data Index: 6471961 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.3092. Min Act: -0.1700
Data Index: 3927990 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.2780. Min Act: -0.1700
Data Index: 2092585 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.2467. Min Act: -0.1700
Data Index: 1134605 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1842. Min Act: -0.1700
Data Index: 7433079 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1842. Min Act: -0.1700
Data Index: 4560984 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1842. Min Act: -0.1700
Data Index: 1742540 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1842. Min Act: -0.1700
Data Index: 3981369 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1842. Min Act: -0.1700
Data Index: 7039032 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1530. Min Act: -0.1700
Data Index: 1536135 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1530. Min Act: -0.1700
Data Index: 5247651 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1217. Min Act: -0.1700
Data Index: 3176243 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1530. Min Act: -0.1700
Data Index: 5770566 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1217. Min Act: -0.1700
Data Index: 6577897 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1217. Min Act: -0.1700
Data Index: 2033878 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1217. Min Act: -0.1700
Data Index: 4624692 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.1217. Min Act: -0.1700
Data Index: 5947851 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.0905. Min Act: -0.1700
Data Index: 4411382 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.0592. Min Act: -0.1700
Data Index: 4220686 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3405. Min Range: -4.3405
Max Act: 4.0592. Min Act: -0.1700
Data Index: 4322517 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19