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

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

Neuron 2008 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6180. Min Range: -1.6180

Max Act: 1.6180. Min Act: -0.0000

Data Index: 616486 (C4 (Web Text))

Max Activating Token Index: 1019

Text #1

Max Range: 1.6180. Min Range: -1.6180

Max Act: 1.5828. Min Act: -0.0000

Data Index: 1127260 (C4 (Web Text))

Max Activating Token Index: 302

Text #2

Max Range: 1.6180. Min Range: -1.6180

Max Act: 1.3066. Min Act: -0.0000

Data Index: 68473 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 1.6180. Min Range: -1.6180

Max Act: 1.2281. Min Act: -0.0000

Data Index: 518778 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 1.6180. Min Range: -1.6180

Max Act: 1.0423. Min Act: -0.0000

Data Index: 314262 (C4 (Web Text))

Max Activating Token Index: 726

Text #5

Max Range: 1.6180. Min Range: -1.6180

Max Act: 1.1231. Min Act: -0.0000

Data Index: 416302 (C4 (Web Text))

Max Activating Token Index: 987

Text #6

Max Range: 1.6180. Min Range: -1.6180

Max Act: 1.0780. Min Act: -0.0000

Data Index: 287676 (C4 (Web Text))

Max Activating Token Index: 873

Text #7

Max Range: 1.6180. Min Range: -1.6180

Max Act: 1.0779. Min Act: -0.0000

Data Index: 486300 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 1.6180. Min Range: -1.6180

Max Act: 1.0720. Min Act: -0.0000

Data Index: 1090949 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 1.6180. Min Range: -1.6180

Max Act: 0.9764. Min Act: -0.0000

Data Index: 699168 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 1.6180. Min Range: -1.6180

Max Act: 0.9384. Min Act: -0.0000

Data Index: 868293 (C4 (Web Text))

Max Activating Token Index: 958

Text #11

Max Range: 1.6180. Min Range: -1.6180

Max Act: 0.9884. Min Act: -0.0000

Data Index: 1299575 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 1.6180. Min Range: -1.6180

Max Act: 0.9853. Min Act: -0.0000

Data Index: 524485 (C4 (Web Text))

Max Activating Token Index: 726

Text #13

Max Range: 1.6180. Min Range: -1.6180

Max Act: 1.0153. Min Act: -0.0000

Data Index: 101575 (C4 (Web Text))

Max Activating Token Index: 974

Text #14

Max Range: 1.6180. Min Range: -1.6180

Max Act: 0.9794. Min Act: -0.0000

Data Index: 62790 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 1.6180. Min Range: -1.6180

Max Act: 0.9248. Min Act: -0.0000

Data Index: 108592 (C4 (Web Text))

Max Activating Token Index: 491

Text #16

Max Range: 1.6180. Min Range: -1.6180

Max Act: 1.0394. Min Act: -0.0000

Data Index: 1034038 (C4 (Web Text))

Max Activating Token Index: 234

Text #17

Max Range: 1.6180. Min Range: -1.6180

Max Act: 0.9118. Min Act: -0.0000

Data Index: 1190014 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 1.6180. Min Range: -1.6180

Max Act: 0.9154. Min Act: -0.0000

Data Index: 796856 (C4 (Web Text))

Max Activating Token Index: 317

Text #19

Max Range: 1.6180. Min Range: -1.6180

Max Act: 0.9562. Min Act: -0.0000

Data Index: 1200084 (C4 (Web Text))

Max Activating Token Index: 689