Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2971 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0436. Min Act: -0.0002

Data Index: 912635 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0484. Min Act: -0.0002

Data Index: 531333 (C4 (Web Text))

Max Activating Token Index: 80

Text #2

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0418. Min Act: -0.0002

Data Index: 320490 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0384. Min Act: -0.0002

Data Index: 49149 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0457. Min Act: -0.0002

Data Index: 743614 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0445. Min Act: -0.0002

Data Index: 13931 (C4 (Web Text))

Max Activating Token Index: 8

Text #6

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0447. Min Act: -0.0002

Data Index: 609727 (C4 (Web Text))

Max Activating Token Index: 745

Text #7

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0457. Min Act: -0.0002

Data Index: 141879 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0381. Min Act: -0.0002

Data Index: 986469 (C4 (Web Text))

Max Activating Token Index: 210

Text #9

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0411. Min Act: -0.0002

Data Index: 183908 (C4 (Web Text))

Max Activating Token Index: 659

Text #10

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1185820 (C4 (Web Text))

Max Activating Token Index: 425

Text #11

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0378. Min Act: -0.0002

Data Index: 316660 (C4 (Web Text))

Max Activating Token Index: 726

Text #12

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0396. Min Act: -0.0002

Data Index: 233718 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0405. Min Act: -0.0002

Data Index: 83477 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0442. Min Act: -0.0002

Data Index: 786875 (C4 (Web Text))

Max Activating Token Index: 531

Text #15

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0395. Min Act: -0.0002

Data Index: 426204 (C4 (Web Text))

Max Activating Token Index: 666

Text #16

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0376. Min Act: -0.0002

Data Index: 360672 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0421. Min Act: -0.0002

Data Index: 425583 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0430. Min Act: -0.0002

Data Index: 404555 (C4 (Web Text))

Max Activating Token Index: 353

Text #19

Max Range: 0.0484. Min Range: -0.0484

Max Act: 0.0316. Min Act: -0.0002

Data Index: 1218687 (C4 (Web Text))

Max Activating Token Index: 221