Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3591 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5359. Min Range: -8.5359
Max Act: 8.5359. Min Act: -0.1700
Data Index: 5448854 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5359. Min Range: -8.5359
Max Act: 8.4109. Min Act: -0.1700
Data Index: 3262655 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5359. Min Range: -8.5359
Max Act: 8.2234. Min Act: -0.1700
Data Index: 6348915 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5359. Min Range: -8.5359
Max Act: 8.2859. Min Act: -0.1700
Data Index: 1560771 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5359. Min Range: -8.5359
Max Act: 8.2234. Min Act: -0.1700
Data Index: 4128481 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5359. Min Range: -8.5359
Max Act: 7.9734. Min Act: -0.1700
Data Index: 4177706 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5359. Min Range: -8.5359
Max Act: 7.9422. Min Act: -0.1700
Data Index: 6874720 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5359. Min Range: -8.5359
Max Act: 7.9422. Min Act: -0.1700
Data Index: 3217386 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5359. Min Range: -8.5359
Max Act: 7.9109. Min Act: -0.1700
Data Index: 4893004 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5359. Min Range: -8.5359
Max Act: 7.8797. Min Act: -0.1700
Data Index: 8100507 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5359. Min Range: -8.5359
Max Act: 7.8172. Min Act: -0.1700
Data Index: 1868869 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5359. Min Range: -8.5359
Max Act: 7.8172. Min Act: -0.1700
Data Index: 4644639 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5359. Min Range: -8.5359
Max Act: 7.8172. Min Act: -0.1700
Data Index: 1945330 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5359. Min Range: -8.5359
Max Act: 7.7859. Min Act: -0.1700
Data Index: 514743 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5359. Min Range: -8.5359
Max Act: 7.7234. Min Act: -0.1700
Data Index: 8192625 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5359. Min Range: -8.5359
Max Act: 7.7547. Min Act: -0.1700
Data Index: 3844394 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5359. Min Range: -8.5359
Max Act: 7.7234. Min Act: -0.1700
Data Index: 7808546 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5359. Min Range: -8.5359
Max Act: 7.6922. Min Act: -0.1700
Data Index: 5381646 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5359. Min Range: -8.5359
Max Act: 7.7234. Min Act: -0.1700
Data Index: 5830314 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5359. Min Range: -8.5359
Max Act: 7.6609. Min Act: -0.1700
Data Index: 5503597 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19