Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2078 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.7302. Min Act: -0.0000

Data Index: 204122 (C4 (Web Text))

Max Activating Token Index: 1000

Text #1

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6864. Min Act: -0.0000

Data Index: 961416 (C4 (Web Text))

Max Activating Token Index: 866

Text #2

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6513. Min Act: -0.0000

Data Index: 353632 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6610. Min Act: -0.0000

Data Index: 832971 (C4 (Web Text))

Max Activating Token Index: 984

Text #4

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6201. Min Act: 0.0000

Data Index: 900397 (C4 (Web Text))

Max Activating Token Index: 249

Text #5

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6188. Min Act: -0.0000

Data Index: 911301 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5978. Min Act: -0.0000

Data Index: 341418 (C4 (Web Text))

Max Activating Token Index: 191

Text #7

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5878. Min Act: -0.0000

Data Index: 1261445 (C4 (Web Text))

Max Activating Token Index: 966

Text #8

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5807. Min Act: -0.0000

Data Index: 290495 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5761. Min Act: -0.0000

Data Index: 236410 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5575. Min Act: 0.0000

Data Index: 837822 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5745. Min Act: -0.0000

Data Index: 347872 (C4 (Web Text))

Max Activating Token Index: 903

Text #12

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5371. Min Act: -0.0000

Data Index: 424812 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5642. Min Act: -0.0000

Data Index: 823333 (C4 (Web Text))

Max Activating Token Index: 850

Text #14

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5217. Min Act: -0.0000

Data Index: 738626 (C4 (Web Text))

Max Activating Token Index: 1002

Text #15

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5551. Min Act: -0.0000

Data Index: 66559 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5377. Min Act: -0.0000

Data Index: 784158 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5313. Min Act: -0.0000

Data Index: 1328942 (C4 (Web Text))

Max Activating Token Index: 808

Text #18

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5187. Min Act: -0.0000

Data Index: 230433 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5148. Min Act: -0.0000

Data Index: 156060 (C4 (Web Text))

Max Activating Token Index: 523