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

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

Neuron 1992 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0386. Min Act: -0.0006

Data Index: 270518 (C4 (Web Text))

Max Activating Token Index: 468

Text #1

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0392. Min Act: -0.0006

Data Index: 4061 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0393. Min Act: -0.0006

Data Index: 561577 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0385. Min Act: -0.0006

Data Index: 959319 (C4 (Web Text))

Max Activating Token Index: 611

Text #4

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0357. Min Act: -0.0005

Data Index: 370006 (C4 (Web Text))

Max Activating Token Index: 970

Text #5

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0396. Min Act: -0.0006

Data Index: 246743 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0372. Min Act: -0.0006

Data Index: 205062 (C4 (Web Text))

Max Activating Token Index: 819

Text #7

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0382. Min Act: -0.0005

Data Index: 206477 (C4 (Web Text))

Max Activating Token Index: 306

Text #8

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0356. Min Act: -0.0006

Data Index: 850269 (C4 (Web Text))

Max Activating Token Index: 994

Text #9

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0384. Min Act: -0.0006

Data Index: 509763 (C4 (Web Text))

Max Activating Token Index: 369

Text #10

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0381. Min Act: -0.0005

Data Index: 988312 (C4 (Web Text))

Max Activating Token Index: 461

Text #11

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0359. Min Act: -0.0006

Data Index: 24609 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0365. Min Act: -0.0006

Data Index: 12094 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0351. Min Act: -0.0006

Data Index: 741780 (C4 (Web Text))

Max Activating Token Index: 910

Text #14

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0373. Min Act: -0.0006

Data Index: 391007 (C4 (Web Text))

Max Activating Token Index: 543

Text #15

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0358. Min Act: -0.0006

Data Index: 1011047 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0365. Min Act: -0.0006

Data Index: 1264925 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0355. Min Act: -0.0006

Data Index: 564561 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0363. Min Act: -0.0006

Data Index: 50625 (C4 (Web Text))

Max Activating Token Index: 850

Text #19

Max Range: 0.0396. Min Range: -0.0396

Max Act: 0.0339. Min Act: -0.0006

Data Index: 35912 (C4 (Web Text))

Max Activating Token Index: 595