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

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

Neuron 1241 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: 0.0414. Min Range: -0.0414

Max Act: 0.0406. Min Act: -0.0003

Data Index: 376197 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0414. Min Act: -0.0003

Data Index: 1326492 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0400. Min Act: -0.0003

Data Index: 635432 (C4 (Web Text))

Max Activating Token Index: 449

Text #3

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0379. Min Act: -0.0003

Data Index: 423463 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0382. Min Act: -0.0003

Data Index: 310538 (C4 (Web Text))

Max Activating Token Index: 217

Text #5

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0380. Min Act: -0.0003

Data Index: 845285 (C4 (Web Text))

Max Activating Token Index: 125

Text #6

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0362. Min Act: -0.0001

Data Index: 946451 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0359. Min Act: -0.0002

Data Index: 1145057 (C4 (Web Text))

Max Activating Token Index: 570

Text #8

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0374. Min Act: -0.0003

Data Index: 947627 (C4 (Web Text))

Max Activating Token Index: 696

Text #9

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0361. Min Act: -0.0003

Data Index: 1003085 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0360. Min Act: -0.0002

Data Index: 884954 (C4 (Web Text))

Max Activating Token Index: 948

Text #11

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0331. Min Act: -0.0003

Data Index: 1206757 (C4 (Web Text))

Max Activating Token Index: 826

Text #12

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0346. Min Act: -0.0003

Data Index: 818914 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0340. Min Act: -0.0003

Data Index: 317650 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0345. Min Act: -0.0004

Data Index: 405041 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0349. Min Act: -0.0001

Data Index: 1057799 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0346. Min Act: -0.0002

Data Index: 405543 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0345. Min Act: -0.0003

Data Index: 630420 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0338. Min Act: -0.0003

Data Index: 857023 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0334. Min Act: -0.0003

Data Index: 1197713 (C4 (Web Text))

Max Activating Token Index: 124