Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3266 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8378. Min Range: -7.8378
Max Act: 7.8378. Min Act: -0.1700
Data Index: 907980 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8378. Min Range: -7.8378
Max Act: 7.8378. Min Act: -0.1700
Data Index: 1556244 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8378. Min Range: -7.8378
Max Act: 7.6190. Min Act: -0.1700
Data Index: 8324881 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8378. Min Range: -7.8378
Max Act: 7.6190. Min Act: -0.1700
Data Index: 5135753 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8378. Min Range: -7.8378
Max Act: 7.5878. Min Act: -0.1700
Data Index: 3479312 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8378. Min Range: -7.8378
Max Act: 7.4003. Min Act: -0.1700
Data Index: 7424226 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8378. Min Range: -7.8378
Max Act: 7.3065. Min Act: -0.1700
Data Index: 3826409 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8378. Min Range: -7.8378
Max Act: 7.3065. Min Act: -0.1700
Data Index: 2839301 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8378. Min Range: -7.8378
Max Act: 7.2753. Min Act: -0.1700
Data Index: 7886068 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8378. Min Range: -7.8378
Max Act: 7.1815. Min Act: -0.1700
Data Index: 7401180 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8378. Min Range: -7.8378
Max Act: 7.2128. Min Act: -0.1700
Data Index: 5579625 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8378. Min Range: -7.8378
Max Act: 7.1503. Min Act: -0.1700
Data Index: 1284662 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8378. Min Range: -7.8378
Max Act: 7.1190. Min Act: -0.1700
Data Index: 3134714 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8378. Min Range: -7.8378
Max Act: 7.1190. Min Act: -0.1700
Data Index: 5638744 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8378. Min Range: -7.8378
Max Act: 7.1190. Min Act: -0.1700
Data Index: 7017744 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8378. Min Range: -7.8378
Max Act: 7.0253. Min Act: -0.1700
Data Index: 7041999 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8378. Min Range: -7.8378
Max Act: 7.0253. Min Act: -0.1700
Data Index: 2008326 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8378. Min Range: -7.8378
Max Act: 7.0565. Min Act: -0.1700
Data Index: 6191465 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8378. Min Range: -7.8378
Max Act: 6.9940. Min Act: -0.1700
Data Index: 8659915 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8378. Min Range: -7.8378
Max Act: 6.9315. Min Act: -0.1700
Data Index: 1297900 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19