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

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

Neuron 3171 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0537. Min Act: -0.0004

Data Index: 523708 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0491. Min Act: -0.0003

Data Index: 113339 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0418. Min Act: -0.0003

Data Index: 1100177 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0409. Min Act: -0.0003

Data Index: 783625 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0384. Min Act: -0.0003

Data Index: 1222967 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0378. Min Act: -0.0003

Data Index: 123500 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0386. Min Act: -0.0003

Data Index: 648934 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0385. Min Act: -0.0003

Data Index: 1069405 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0382. Min Act: -0.0003

Data Index: 986586 (C4 (Web Text))

Max Activating Token Index: 59

Text #9

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0388. Min Act: -0.0003

Data Index: 248033 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0397. Min Act: -0.0004

Data Index: 1346062 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0361. Min Act: -0.0003

Data Index: 420394 (C4 (Web Text))

Max Activating Token Index: 737

Text #12

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0357. Min Act: -0.0003

Data Index: 863576 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0375. Min Act: -0.0003

Data Index: 1096458 (C4 (Web Text))

Max Activating Token Index: 134

Text #14

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0375. Min Act: -0.0003

Data Index: 722381 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0363. Min Act: -0.0003

Data Index: 969893 (C4 (Web Text))

Max Activating Token Index: 515

Text #16

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0372. Min Act: -0.0003

Data Index: 798543 (C4 (Web Text))

Max Activating Token Index: 229

Text #17

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0364. Min Act: -0.0003

Data Index: 85274 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0363. Min Act: -0.0003

Data Index: 1124131 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 0.0537. Min Range: -0.0537

Max Act: 0.0373. Min Act: -0.0003

Data Index: 60004 (C4 (Web Text))

Max Activating Token Index: 234