Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2488 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.8257. Min Range: -1.8257

Max Act: 1.8257. Min Act: -0.0000

Data Index: 509558 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 1.8257. Min Range: -1.8257

Max Act: 1.7458. Min Act: -0.0000

Data Index: 97919 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 1.8257. Min Range: -1.8257

Max Act: 1.6251. Min Act: -0.0000

Data Index: 498671 (C4 (Web Text))

Max Activating Token Index: 951

Text #3

Max Range: 1.8257. Min Range: -1.8257

Max Act: 1.5180. Min Act: -0.0000

Data Index: 1034146 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 1.8257. Min Range: -1.8257

Max Act: 1.5562. Min Act: -0.0000

Data Index: 655934 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 1.8257. Min Range: -1.8257

Max Act: 1.5554. Min Act: -0.0000

Data Index: 739365 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 1.8257. Min Range: -1.8257

Max Act: 1.5440. Min Act: -0.0000

Data Index: 360499 (C4 (Web Text))

Max Activating Token Index: 204

Text #7

Max Range: 1.8257. Min Range: -1.8257

Max Act: 1.5195. Min Act: -0.0000

Data Index: 735512 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 1.8257. Min Range: -1.8257

Max Act: 1.5222. Min Act: -0.0000

Data Index: 487304 (C4 (Web Text))

Max Activating Token Index: 127

Text #9

Max Range: 1.8257. Min Range: -1.8257

Max Act: 1.5252. Min Act: -0.0000

Data Index: 1303291 (C4 (Web Text))

Max Activating Token Index: 203

Text #10

Max Range: 1.8257. Min Range: -1.8257

Max Act: 1.4770. Min Act: -0.0000

Data Index: 869898 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 1.8257. Min Range: -1.8257

Max Act: 1.5696. Min Act: -0.0000

Data Index: 353532 (C4 (Web Text))

Max Activating Token Index: 986

Text #12

Max Range: 1.8257. Min Range: -1.8257

Max Act: 1.4719. Min Act: -0.0000

Data Index: 509246 (C4 (Web Text))

Max Activating Token Index: 193

Text #13

Max Range: 1.8257. Min Range: -1.8257

Max Act: 1.4217. Min Act: -0.0001

Data Index: 814715 (C4 (Web Text))

Max Activating Token Index: 802

Text #14

Max Range: 1.8257. Min Range: -1.8257

Max Act: 1.5338. Min Act: -0.0000

Data Index: 1112639 (C4 (Web Text))

Max Activating Token Index: 463

Text #15

Max Range: 1.8257. Min Range: -1.8257

Max Act: 1.4440. Min Act: -0.0000

Data Index: 201011 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 1.8257. Min Range: -1.8257

Max Act: 1.3424. Min Act: -0.0000

Data Index: 113505 (C4 (Web Text))

Max Activating Token Index: 217

Text #17

Max Range: 1.8257. Min Range: -1.8257

Max Act: 1.4028. Min Act: -0.0001

Data Index: 522715 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 1.8257. Min Range: -1.8257

Max Act: 1.3675. Min Act: -0.0000

Data Index: 1035400 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 1.8257. Min Range: -1.8257

Max Act: 1.3918. Min Act: -0.0000

Data Index: 1018215 (C4 (Web Text))

Max Activating Token Index: 59