Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 170 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0474. Min Act: -0.0002

Data Index: 1217918 (C4 (Web Text))

Max Activating Token Index: 320

Text #1

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0467. Min Act: -0.0003

Data Index: 339192 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0426. Min Act: -0.0003

Data Index: 194878 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0439. Min Act: -0.0002

Data Index: 264838 (C4 (Web Text))

Max Activating Token Index: 956

Text #4

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0430. Min Act: -0.0002

Data Index: 1126962 (C4 (Web Text))

Max Activating Token Index: 395

Text #5

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0425. Min Act: -0.0003

Data Index: 207473 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0406. Min Act: -0.0003

Data Index: 1338448 (C4 (Web Text))

Max Activating Token Index: 270

Text #7

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0412. Min Act: -0.0002

Data Index: 34305 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0390. Min Act: -0.0003

Data Index: 1099240 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0386. Min Act: -0.0003

Data Index: 1004131 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0379. Min Act: -0.0002

Data Index: 230501 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0383. Min Act: -0.0003

Data Index: 678588 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0399. Min Act: -0.0003

Data Index: 691684 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0372. Min Act: -0.0003

Data Index: 737274 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0362. Min Act: -0.0002

Data Index: 188620 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0361. Min Act: -0.0002

Data Index: 889994 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0379. Min Act: -0.0002

Data Index: 258182 (C4 (Web Text))

Max Activating Token Index: 1022

Text #17

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0349. Min Act: -0.0002

Data Index: 1308466 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0379. Min Act: -0.0002

Data Index: 49701 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 0.0474. Min Range: -0.0474

Max Act: 0.0394. Min Act: -0.0002

Data Index: 636972 (C4 (Web Text))

Max Activating Token Index: 272