Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4408 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.7204. Min Act: -0.1700
Data Index: 6321865 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.6579. Min Act: -0.1700
Data Index: 7789648 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.5954. Min Act: -0.1700
Data Index: 416387 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.5954. Min Act: -0.1700
Data Index: 4921769 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.5329. Min Act: -0.1700
Data Index: 6215466 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.4079. Min Act: -0.1700
Data Index: 5725018 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.4079. Min Act: -0.1700
Data Index: 54092 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.4079. Min Act: -0.1700
Data Index: 6233052 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.3766. Min Act: -0.1700
Data Index: 6787636 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.3454. Min Act: -0.1700
Data Index: 5091769 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.3454. Min Act: -0.1700
Data Index: 1272652 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.3141. Min Act: -0.1700
Data Index: 1757338 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.2829. Min Act: -0.1700
Data Index: 1911778 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.2829. Min Act: -0.1700
Data Index: 8713058 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.2829. Min Act: -0.1700
Data Index: 1249130 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.2516. Min Act: -0.1700
Data Index: 2883101 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.2829. Min Act: -0.1700
Data Index: 3191912 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.2829. Min Act: -0.1700
Data Index: 5609227 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.2829. Min Act: -0.1700
Data Index: 5920496 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7204. Min Range: -5.7204
Max Act: 5.2516. Min Act: -0.1700
Data Index: 6364786 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19