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

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

Neuron 1301 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: 0.0416. Min Range: -0.0416

Max Act: 0.0409. Min Act: -0.0003

Data Index: 615391 (C4 (Web Text))

Max Activating Token Index: 551

Text #1

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0416. Min Act: -0.0003

Data Index: 574896 (C4 (Web Text))

Max Activating Token Index: 926

Text #2

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0376. Min Act: -0.0004

Data Index: 98525 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0392. Min Act: -0.0003

Data Index: 420600 (C4 (Web Text))

Max Activating Token Index: 238

Text #4

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0393. Min Act: -0.0003

Data Index: 332958 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0375. Min Act: -0.0003

Data Index: 506958 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0368. Min Act: -0.0003

Data Index: 964048 (C4 (Web Text))

Max Activating Token Index: 737

Text #7

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0356. Min Act: -0.0003

Data Index: 65995 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0358. Min Act: -0.0003

Data Index: 166656 (C4 (Web Text))

Max Activating Token Index: 924

Text #9

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0342. Min Act: -0.0003

Data Index: 1114796 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0390. Min Act: -0.0004

Data Index: 475580 (C4 (Web Text))

Max Activating Token Index: 626

Text #11

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0382. Min Act: -0.0004

Data Index: 72546 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0341. Min Act: -0.0003

Data Index: 518564 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0378. Min Act: -0.0003

Data Index: 249809 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0364. Min Act: -0.0004

Data Index: 101192 (C4 (Web Text))

Max Activating Token Index: 657

Text #15

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0363. Min Act: -0.0003

Data Index: 707930 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0353. Min Act: -0.0004

Data Index: 1216042 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0359. Min Act: -0.0003

Data Index: 197873 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0377. Min Act: -0.0003

Data Index: 17784 (C4 (Web Text))

Max Activating Token Index: 1011

Text #19

Max Range: 0.0416. Min Range: -0.0416

Max Act: 0.0371. Min Act: -0.0003

Data Index: 437930 (C4 (Web Text))

Max Activating Token Index: 472