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

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

Neuron 3431 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2680. Min Act: -0.0000

Data Index: 450110 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2750. Min Act: -0.0000

Data Index: 871664 (C4 (Web Text))

Max Activating Token Index: 551

Text #2

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2554. Min Act: -0.0000

Data Index: 440024 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2504. Min Act: -0.0000

Data Index: 1330272 (C4 (Web Text))

Max Activating Token Index: 596

Text #4

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2509. Min Act: 0.0000

Data Index: 531636 (C4 (Web Text))

Max Activating Token Index: 545

Text #5

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2404. Min Act: 0.0000

Data Index: 1150003 (C4 (Web Text))

Max Activating Token Index: 979

Text #6

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2441. Min Act: -0.0000

Data Index: 705489 (C4 (Web Text))

Max Activating Token Index: 559

Text #7

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2415. Min Act: 0.0000

Data Index: 101404 (C4 (Web Text))

Max Activating Token Index: 366

Text #8

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2397. Min Act: -0.0000

Data Index: 200254 (C4 (Web Text))

Max Activating Token Index: 504

Text #9

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2321. Min Act: -0.0000

Data Index: 1354655 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2334. Min Act: -0.0000

Data Index: 1112614 (C4 (Web Text))

Max Activating Token Index: 655

Text #11

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2312. Min Act: -0.0000

Data Index: 1302064 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2186. Min Act: 0.0000

Data Index: 1108395 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2274. Min Act: -0.0000

Data Index: 467337 (C4 (Web Text))

Max Activating Token Index: 823

Text #14

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2184. Min Act: -0.0000

Data Index: 666497 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2185. Min Act: 0.0001

Data Index: 325297 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2213. Min Act: -0.0000

Data Index: 418522 (C4 (Web Text))

Max Activating Token Index: 275

Text #17

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2161. Min Act: -0.0000

Data Index: 1033903 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2096. Min Act: -0.0000

Data Index: 680353 (C4 (Web Text))

Max Activating Token Index: 453

Text #19

Max Range: 0.2750. Min Range: -0.2750

Max Act: 0.2059. Min Act: -0.0000

Data Index: 852439 (C4 (Web Text))

Max Activating Token Index: 691