Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 607 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0379. Min Act: -0.0002

Data Index: 685391 (C4 (Web Text))

Max Activating Token Index: 873

Text #1

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0376. Min Act: -0.0002

Data Index: 640305 (C4 (Web Text))

Max Activating Token Index: 387

Text #2

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0367. Min Act: -0.0002

Data Index: 766408 (C4 (Web Text))

Max Activating Token Index: 200

Text #3

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0377. Min Act: -0.0002

Data Index: 13403 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0359. Min Act: -0.0002

Data Index: 840918 (C4 (Web Text))

Max Activating Token Index: 394

Text #5

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0360. Min Act: -0.0002

Data Index: 1190004 (C4 (Web Text))

Max Activating Token Index: 992

Text #6

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0362. Min Act: -0.0002

Data Index: 620177 (C4 (Web Text))

Max Activating Token Index: 468

Text #7

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0354. Min Act: -0.0002

Data Index: 96093 (C4 (Web Text))

Max Activating Token Index: 63

Text #8

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0338. Min Act: -0.0002

Data Index: 534595 (C4 (Web Text))

Max Activating Token Index: 493

Text #9

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0340. Min Act: -0.0002

Data Index: 768119 (C4 (Web Text))

Max Activating Token Index: 180

Text #10

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0331. Min Act: -0.0002

Data Index: 37520 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0331. Min Act: -0.0002

Data Index: 573926 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0321. Min Act: -0.0002

Data Index: 961140 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0326. Min Act: -0.0002

Data Index: 1253366 (C4 (Web Text))

Max Activating Token Index: 846

Text #14

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0317. Min Act: -0.0002

Data Index: 421428 (C4 (Web Text))

Max Activating Token Index: 647

Text #15

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0336. Min Act: -0.0002

Data Index: 557856 (C4 (Web Text))

Max Activating Token Index: 915

Text #16

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0325. Min Act: -0.0002

Data Index: 406857 (C4 (Web Text))

Max Activating Token Index: 567

Text #17

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0324. Min Act: -0.0002

Data Index: 209311 (C4 (Web Text))

Max Activating Token Index: 958

Text #18

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0326. Min Act: -0.0002

Data Index: 1234214 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 0.0379. Min Range: -0.0379

Max Act: 0.0330. Min Act: -0.0002

Data Index: 917925 (C4 (Web Text))

Max Activating Token Index: 1020