Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 708 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5833. Min Range: -4.5833
Max Act: 4.5833. Min Act: -0.1700
Data Index: 6833982 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5833. Min Range: -4.5833
Max Act: 4.3646. Min Act: -0.1700
Data Index: 1065193 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5833. Min Range: -4.5833
Max Act: 4.2396. Min Act: -0.1700
Data Index: 6684377 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5833. Min Range: -4.5833
Max Act: 4.2083. Min Act: -0.1700
Data Index: 1002225 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5833. Min Range: -4.5833
Max Act: 4.1771. Min Act: -0.1700
Data Index: 6736399 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5833. Min Range: -4.5833
Max Act: 4.1458. Min Act: -0.1700
Data Index: 7615365 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5833. Min Range: -4.5833
Max Act: 4.0833. Min Act: -0.1700
Data Index: 2420501 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5833. Min Range: -4.5833
Max Act: 4.0520. Min Act: -0.1700
Data Index: 3123860 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5833. Min Range: -4.5833
Max Act: 4.0208. Min Act: -0.1700
Data Index: 2493721 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5833. Min Range: -4.5833
Max Act: 4.0833. Min Act: -0.1700
Data Index: 4844538 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5833. Min Range: -4.5833
Max Act: 4.0208. Min Act: -0.1700
Data Index: 5958772 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5833. Min Range: -4.5833
Max Act: 4.0208. Min Act: -0.1700
Data Index: 419034 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5833. Min Range: -4.5833
Max Act: 3.9895. Min Act: -0.1700
Data Index: 8412896 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5833. Min Range: -4.5833
Max Act: 3.9895. Min Act: -0.1700
Data Index: 6126690 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5833. Min Range: -4.5833
Max Act: 3.9582. Min Act: -0.1700
Data Index: 381355 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5833. Min Range: -4.5833
Max Act: 3.9582. Min Act: -0.1700
Data Index: 7946542 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5833. Min Range: -4.5833
Max Act: 3.9582. Min Act: -0.1700
Data Index: 2597004 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5833. Min Range: -4.5833
Max Act: 3.9582. Min Act: -0.1700
Data Index: 7715752 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5833. Min Range: -4.5833
Max Act: 3.9582. Min Act: -0.1700
Data Index: 144024 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5833. Min Range: -4.5833
Max Act: 3.9270. Min Act: -0.1700
Data Index: 600143 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19