Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3990 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9266. Min Range: -4.9266
Max Act: 4.9266. Min Act: -0.1700
Data Index: 392736 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9266. Min Range: -4.9266
Max Act: 4.8954. Min Act: -0.1700
Data Index: 553805 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9266. Min Range: -4.9266
Max Act: 4.7391. Min Act: -0.1700
Data Index: 3005754 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9266. Min Range: -4.9266
Max Act: 4.6454. Min Act: -0.1700
Data Index: 1937861 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9266. Min Range: -4.9266
Max Act: 4.6454. Min Act: -0.1700
Data Index: 1500665 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9266. Min Range: -4.9266
Max Act: 4.5829. Min Act: -0.1700
Data Index: 4021322 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9266. Min Range: -4.9266
Max Act: 4.6141. Min Act: -0.1700
Data Index: 7917907 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9266. Min Range: -4.9266
Max Act: 4.6141. Min Act: -0.1700
Data Index: 5746949 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9266. Min Range: -4.9266
Max Act: 4.5516. Min Act: -0.1700
Data Index: 7729818 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9266. Min Range: -4.9266
Max Act: 4.5516. Min Act: -0.1700
Data Index: 1902210 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9266. Min Range: -4.9266
Max Act: 4.5204. Min Act: -0.1700
Data Index: 7601614 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9266. Min Range: -4.9266
Max Act: 4.4891. Min Act: -0.1700
Data Index: 7850506 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9266. Min Range: -4.9266
Max Act: 4.4891. Min Act: -0.1688
Data Index: 2277607 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9266. Min Range: -4.9266
Max Act: 4.4891. Min Act: -0.1700
Data Index: 1581813 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9266. Min Range: -4.9266
Max Act: 4.4579. Min Act: -0.1700
Data Index: 5342631 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9266. Min Range: -4.9266
Max Act: 4.4579. Min Act: -0.1700
Data Index: 3438082 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9266. Min Range: -4.9266
Max Act: 4.4579. Min Act: -0.1700
Data Index: 186527 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9266. Min Range: -4.9266
Max Act: 4.4579. Min Act: -0.1700
Data Index: 823192 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9266. Min Range: -4.9266
Max Act: 4.4579. Min Act: -0.1700
Data Index: 2411362 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9266. Min Range: -4.9266
Max Act: 4.4266. Min Act: -0.1700
Data Index: 1429440 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #19