Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1917 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4221. Min Range: -5.4221
Max Act: 5.4221. Min Act: -0.1700
Data Index: 6662158 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4221. Min Range: -5.4221
Max Act: 5.2659. Min Act: -0.1700
Data Index: 587429 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4221. Min Range: -5.4221
Max Act: 5.1409. Min Act: -0.1700
Data Index: 7397095 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4221. Min Range: -5.4221
Max Act: 5.1096. Min Act: -0.1700
Data Index: 6650305 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4221. Min Range: -5.4221
Max Act: 5.1096. Min Act: -0.1700
Data Index: 6878250 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4221. Min Range: -5.4221
Max Act: 5.0784. Min Act: -0.1700
Data Index: 1969657 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4221. Min Range: -5.4221
Max Act: 5.0784. Min Act: -0.1700
Data Index: 2498078 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4221. Min Range: -5.4221
Max Act: 5.0159. Min Act: -0.1700
Data Index: 941318 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4221. Min Range: -5.4221
Max Act: 4.9534. Min Act: -0.1700
Data Index: 1756219 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4221. Min Range: -5.4221
Max Act: 4.9534. Min Act: -0.1700
Data Index: 1024575 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4221. Min Range: -5.4221
Max Act: 4.8909. Min Act: -0.1700
Data Index: 8223226 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4221. Min Range: -5.4221
Max Act: 4.9221. Min Act: -0.1700
Data Index: 1468595 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4221. Min Range: -5.4221
Max Act: 4.9221. Min Act: -0.1700
Data Index: 4249437 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4221. Min Range: -5.4221
Max Act: 4.9221. Min Act: -0.1700
Data Index: 1142773 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4221. Min Range: -5.4221
Max Act: 4.8909. Min Act: -0.1700
Data Index: 900977 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4221. Min Range: -5.4221
Max Act: 4.8909. Min Act: -0.1700
Data Index: 8288970 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4221. Min Range: -5.4221
Max Act: 4.8909. Min Act: -0.1700
Data Index: 6470628 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4221. Min Range: -5.4221
Max Act: 4.8596. Min Act: -0.1700
Data Index: 7563746 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4221. Min Range: -5.4221
Max Act: 4.8596. Min Act: -0.1700
Data Index: 230768 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4221. Min Range: -5.4221
Max Act: 4.8909. Min Act: -0.1700
Data Index: 5540054 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19