Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3704 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0526. Min Act: -0.0001

Data Index: 1231563 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0515. Min Act: -0.0001

Data Index: 325407 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0457. Min Act: -0.0001

Data Index: 1154239 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0452. Min Act: -0.0001

Data Index: 704826 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0381. Min Act: -0.0001

Data Index: 1316677 (C4 (Web Text))

Max Activating Token Index: 370

Text #5

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0403. Min Act: -0.0001

Data Index: 1210105 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0443. Min Act: -0.0001

Data Index: 130576 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0376. Min Act: -0.0001

Data Index: 228783 (C4 (Web Text))

Max Activating Token Index: 655

Text #8

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0463. Min Act: -0.0001

Data Index: 817933 (C4 (Web Text))

Max Activating Token Index: 501

Text #9

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0403. Min Act: -0.0001

Data Index: 1116433 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0348. Min Act: -0.0001

Data Index: 580758 (C4 (Web Text))

Max Activating Token Index: 576

Text #11

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0376. Min Act: -0.0001

Data Index: 1064010 (C4 (Web Text))

Max Activating Token Index: 280

Text #12

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0411. Min Act: -0.0001

Data Index: 791750 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0371. Min Act: -0.0001

Data Index: 281342 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0358. Min Act: -0.0001

Data Index: 771899 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0415. Min Act: -0.0001

Data Index: 190476 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0407. Min Act: -0.0001

Data Index: 901195 (C4 (Web Text))

Max Activating Token Index: 430

Text #17

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0323. Min Act: -0.0001

Data Index: 971678 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0340. Min Act: -0.0001

Data Index: 291812 (C4 (Web Text))

Max Activating Token Index: 748

Text #19

Max Range: 0.0526. Min Range: -0.0526

Max Act: 0.0376. Min Act: -0.0001

Data Index: 686134 (C4 (Web Text))

Max Activating Token Index: 356