Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3378 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1435. Min Range: -6.1435
Max Act: 6.1435. Min Act: -0.1700
Data Index: 5007702 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1435. Min Range: -6.1435
Max Act: 6.0498. Min Act: -0.1700
Data Index: 4034066 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1435. Min Range: -6.1435
Max Act: 5.9873. Min Act: -0.1700
Data Index: 736085 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1435. Min Range: -6.1435
Max Act: 5.9248. Min Act: -0.1700
Data Index: 1201769 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1435. Min Range: -6.1435
Max Act: 5.8935. Min Act: -0.1700
Data Index: 6547522 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1435. Min Range: -6.1435
Max Act: 5.8310. Min Act: -0.1700
Data Index: 736084 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1435. Min Range: -6.1435
Max Act: 5.8310. Min Act: -0.1700
Data Index: 8680291 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1435. Min Range: -6.1435
Max Act: 5.8310. Min Act: -0.1700
Data Index: 875639 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1435. Min Range: -6.1435
Max Act: 5.8310. Min Act: -0.1700
Data Index: 1201771 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1435. Min Range: -6.1435
Max Act: 5.7998. Min Act: -0.1700
Data Index: 379531 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1435. Min Range: -6.1435
Max Act: 5.7998. Min Act: -0.1700
Data Index: 875640 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1435. Min Range: -6.1435
Max Act: 5.7998. Min Act: -0.1700
Data Index: 3034620 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1435. Min Range: -6.1435
Max Act: 5.7685. Min Act: -0.1700
Data Index: 3289146 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1435. Min Range: -6.1435
Max Act: 5.7373. Min Act: -0.1700
Data Index: 5120170 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1435. Min Range: -6.1435
Max Act: 5.7685. Min Act: -0.1700
Data Index: 7308548 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1435. Min Range: -6.1435
Max Act: 5.7685. Min Act: -0.1700
Data Index: 4584530 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1435. Min Range: -6.1435
Max Act: 5.7373. Min Act: -0.1700
Data Index: 6876379 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1435. Min Range: -6.1435
Max Act: 5.7373. Min Act: -0.1700
Data Index: 5007701 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1435. Min Range: -6.1435
Max Act: 5.7373. Min Act: -0.1700
Data Index: 4457298 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1435. Min Range: -6.1435
Max Act: 5.7060. Min Act: -0.1700
Data Index: 5007698 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19