Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3551 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5008. Min Range: -8.5008
Max Act: 8.5008. Min Act: -0.1700
Data Index: 7050477 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5008. Min Range: -8.5008
Max Act: 8.5008. Min Act: -0.1700
Data Index: 8472295 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5008. Min Range: -8.5008
Max Act: 8.3133. Min Act: -0.1700
Data Index: 6756490 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5008. Min Range: -8.5008
Max Act: 8.3133. Min Act: -0.1700
Data Index: 8239621 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5008. Min Range: -8.5008
Max Act: 8.2508. Min Act: -0.1700
Data Index: 7819630 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5008. Min Range: -8.5008
Max Act: 8.2508. Min Act: -0.1700
Data Index: 3445718 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5008. Min Range: -8.5008
Max Act: 8.1258. Min Act: -0.1700
Data Index: 5678437 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5008. Min Range: -8.5008
Max Act: 8.1571. Min Act: -0.1700
Data Index: 3685664 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5008. Min Range: -8.5008
Max Act: 8.1571. Min Act: -0.1700
Data Index: 6618722 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5008. Min Range: -8.5008
Max Act: 8.1258. Min Act: -0.1700
Data Index: 323621 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5008. Min Range: -8.5008
Max Act: 8.1571. Min Act: -0.1700
Data Index: 2426528 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5008. Min Range: -8.5008
Max Act: 8.1883. Min Act: -0.1700
Data Index: 8519394 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5008. Min Range: -8.5008
Max Act: 8.1258. Min Act: -0.1700
Data Index: 5994075 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5008. Min Range: -8.5008
Max Act: 8.0946. Min Act: -0.1700
Data Index: 2334204 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5008. Min Range: -8.5008
Max Act: 8.0633. Min Act: -0.1700
Data Index: 4052100 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5008. Min Range: -8.5008
Max Act: 8.0321. Min Act: -0.1700
Data Index: 5354371 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5008. Min Range: -8.5008
Max Act: 8.0321. Min Act: -0.1700
Data Index: 2006696 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5008. Min Range: -8.5008
Max Act: 8.0321. Min Act: -0.1700
Data Index: 8691584 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5008. Min Range: -8.5008
Max Act: 7.9696. Min Act: -0.1700
Data Index: 2707358 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5008. Min Range: -8.5008
Max Act: 7.9696. Min Act: -0.1700
Data Index: 8562327 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #19