Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3389 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.3479. Min Act: -0.1700
Data Index: 2779981 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.3479. Min Act: -0.1700
Data Index: 6682796 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.3322. Min Act: -0.1700
Data Index: 3888019 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.3322. Min Act: -0.1700
Data Index: 929861 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.3165. Min Act: -0.1700
Data Index: 4414594 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.3008. Min Act: -0.1700
Data Index: 917751 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.3008. Min Act: -0.1700
Data Index: 4580155 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.3165. Min Act: -0.1700
Data Index: 4398102 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.3008. Min Act: -0.1700
Data Index: 8592644 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.3008. Min Act: -0.1700
Data Index: 1482292 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.2851. Min Act: -0.1700
Data Index: 5399910 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.2694. Min Act: -0.1700
Data Index: 3914863 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.2694. Min Act: -0.1700
Data Index: 6963866 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.2537. Min Act: -0.1700
Data Index: 11978 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.2537. Min Act: -0.1700
Data Index: 6217325 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.2694. Min Act: -0.1700
Data Index: 1743033 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.2694. Min Act: -0.1700
Data Index: 2170723 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.2537. Min Act: -0.1700
Data Index: 4487638 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.2537. Min Act: -0.1700
Data Index: 6018690 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3479. Min Range: -3.3479
Max Act: 3.2379. Min Act: -0.1700
Data Index: 1082839 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #19