Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4522 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.7301. Min Range: -4.7301
Max Act: 4.7301. Min Act: -0.1700
Data Index: 767411 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7301. Min Range: -4.7301
Max Act: 4.7301. Min Act: -0.1700
Data Index: 5843275 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7301. Min Range: -4.7301
Max Act: 4.6989. Min Act: -0.1700
Data Index: 2002861 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7301. Min Range: -4.7301
Max Act: 4.6676. Min Act: -0.1700
Data Index: 4718363 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7301. Min Range: -4.7301
Max Act: 4.6676. Min Act: -0.1700
Data Index: 457933 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7301. Min Range: -4.7301
Max Act: 4.6364. Min Act: -0.1700
Data Index: 1312524 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7301. Min Range: -4.7301
Max Act: 4.6364. Min Act: -0.1700
Data Index: 3276158 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7301. Min Range: -4.7301
Max Act: 4.6364. Min Act: -0.1700
Data Index: 4059514 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7301. Min Range: -4.7301
Max Act: 4.5739. Min Act: -0.1700
Data Index: 2089202 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7301. Min Range: -4.7301
Max Act: 4.5739. Min Act: -0.1700
Data Index: 1763727 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7301. Min Range: -4.7301
Max Act: 4.6051. Min Act: -0.1700
Data Index: 5575620 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7301. Min Range: -4.7301
Max Act: 4.5739. Min Act: -0.1700
Data Index: 5575619 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7301. Min Range: -4.7301
Max Act: 4.5739. Min Act: -0.1700
Data Index: 2089198 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7301. Min Range: -4.7301
Max Act: 4.5739. Min Act: -0.1700
Data Index: 1824206 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7301. Min Range: -4.7301
Max Act: 4.5739. Min Act: -0.1700
Data Index: 2002864 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7301. Min Range: -4.7301
Max Act: 4.5739. Min Act: -0.1700
Data Index: 1994463 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7301. Min Range: -4.7301
Max Act: 4.5426. Min Act: -0.1700
Data Index: 5561306 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7301. Min Range: -4.7301
Max Act: 4.5114. Min Act: -0.1700
Data Index: 3578042 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7301. Min Range: -4.7301
Max Act: 4.5426. Min Act: -0.1700
Data Index: 3817102 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7301. Min Range: -4.7301
Max Act: 4.5426. Min Act: -0.1700
Data Index: 1138246 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #19