Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3492 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8490. Min Range: -6.8490
Max Act: 6.8490. Min Act: -0.1700
Data Index: 2010871 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8490. Min Range: -6.8490
Max Act: 6.6302. Min Act: -0.1700
Data Index: 2247872 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8490. Min Range: -6.8490
Max Act: 6.5990. Min Act: -0.1700
Data Index: 7948529 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8490. Min Range: -6.8490
Max Act: 6.5677. Min Act: -0.1700
Data Index: 12190 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8490. Min Range: -6.8490
Max Act: 6.5365. Min Act: -0.1700
Data Index: 5390624 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8490. Min Range: -6.8490
Max Act: 6.5052. Min Act: -0.1700
Data Index: 3182494 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8490. Min Range: -6.8490
Max Act: 6.4740. Min Act: -0.1700
Data Index: 2469528 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8490. Min Range: -6.8490
Max Act: 6.4740. Min Act: -0.1700
Data Index: 3745280 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8490. Min Range: -6.8490
Max Act: 6.5052. Min Act: -0.1700
Data Index: 1601431 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8490. Min Range: -6.8490
Max Act: 6.4740. Min Act: -0.1700
Data Index: 4168067 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8490. Min Range: -6.8490
Max Act: 6.4740. Min Act: -0.1700
Data Index: 3169944 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8490. Min Range: -6.8490
Max Act: 6.4427. Min Act: -0.1700
Data Index: 6169245 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8490. Min Range: -6.8490
Max Act: 6.4427. Min Act: -0.1700
Data Index: 1513481 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8490. Min Range: -6.8490
Max Act: 6.4427. Min Act: -0.1700
Data Index: 8608642 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8490. Min Range: -6.8490
Max Act: 6.4115. Min Act: -0.1700
Data Index: 3653182 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8490. Min Range: -6.8490
Max Act: 6.4427. Min Act: -0.1700
Data Index: 6115405 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8490. Min Range: -6.8490
Max Act: 6.4115. Min Act: -0.1700
Data Index: 695108 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8490. Min Range: -6.8490
Max Act: 6.4115. Min Act: -0.1700
Data Index: 810076 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8490. Min Range: -6.8490
Max Act: 6.3802. Min Act: -0.1700
Data Index: 2585112 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8490. Min Range: -6.8490
Max Act: 6.4115. Min Act: -0.1700
Data Index: 6273697 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #19