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

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

Neuron 3403 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0423. Min Act: -0.0001

Data Index: 636344 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0417. Min Act: -0.0001

Data Index: 936494 (C4 (Web Text))

Max Activating Token Index: 993

Text #2

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0372. Min Act: -0.0001

Data Index: 813294 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0362. Min Act: -0.0001

Data Index: 1086662 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0350. Min Act: -0.0001

Data Index: 1251179 (C4 (Web Text))

Max Activating Token Index: 422

Text #5

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0348. Min Act: -0.0001

Data Index: 42390 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0326. Min Act: -0.0001

Data Index: 443735 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0148. Min Act: -0.0001

Data Index: 945990 (C4 (Web Text))

Max Activating Token Index: 581

Text #8

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0306. Min Act: -0.0001

Data Index: 1087154 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0303. Min Act: -0.0001

Data Index: 732934 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0210. Min Act: -0.0001

Data Index: 1218968 (C4 (Web Text))

Max Activating Token Index: 296

Text #11

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0336. Min Act: -0.0001

Data Index: 604060 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0300. Min Act: -0.0001

Data Index: 747893 (C4 (Web Text))

Max Activating Token Index: 520

Text #13

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0263. Min Act: -0.0001

Data Index: 10559 (C4 (Web Text))

Max Activating Token Index: 166

Text #14

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0321. Min Act: -0.0001

Data Index: 1130936 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0320. Min Act: -0.0001

Data Index: 259078 (C4 (Web Text))

Max Activating Token Index: 937

Text #16

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0301. Min Act: -0.0001

Data Index: 282178 (C4 (Web Text))

Max Activating Token Index: 169

Text #17

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0289. Min Act: -0.0001

Data Index: 691469 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0294. Min Act: -0.0001

Data Index: 1417675 (Python Code)

Max Activating Token Index: 513

Text #19

Max Range: 0.0423. Min Range: -0.0423

Max Act: 0.0205. Min Act: -0.0001

Data Index: 1294555 (C4 (Web Text))

Max Activating Token Index: 680