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

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

Neuron 1381 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0282. Min Act: -0.0001

Data Index: 177698 (C4 (Web Text))

Max Activating Token Index: 471

Text #1

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0290. Min Act: -0.0001

Data Index: 59493 (C4 (Web Text))

Max Activating Token Index: 244

Text #2

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0274. Min Act: -0.0002

Data Index: 1233589 (C4 (Web Text))

Max Activating Token Index: 447

Text #3

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0266. Min Act: -0.0002

Data Index: 266065 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0265. Min Act: -0.0001

Data Index: 11455 (C4 (Web Text))

Max Activating Token Index: 306

Text #5

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0264. Min Act: -0.0001

Data Index: 959612 (C4 (Web Text))

Max Activating Token Index: 653

Text #6

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0264. Min Act: -0.0002

Data Index: 573170 (C4 (Web Text))

Max Activating Token Index: 1013

Text #7

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0260. Min Act: -0.0002

Data Index: 111462 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0245. Min Act: -0.0002

Data Index: 1203278 (C4 (Web Text))

Max Activating Token Index: 954

Text #9

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0235. Min Act: -0.0002

Data Index: 292128 (C4 (Web Text))

Max Activating Token Index: 326

Text #10

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0230. Min Act: -0.0002

Data Index: 255796 (C4 (Web Text))

Max Activating Token Index: 892

Text #11

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0225. Min Act: -0.0002

Data Index: 849383 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0225. Min Act: -0.0002

Data Index: 1371571 (Python Code)

Max Activating Token Index: 22

Text #13

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0220. Min Act: -0.0001

Data Index: 545028 (C4 (Web Text))

Max Activating Token Index: 178

Text #14

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0218. Min Act: -0.0002

Data Index: 242134 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0218. Min Act: -0.0002

Data Index: 773988 (C4 (Web Text))

Max Activating Token Index: 245

Text #16

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0215. Min Act: -0.0002

Data Index: 311758 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0206. Min Act: -0.0002

Data Index: 971745 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0210. Min Act: -0.0002

Data Index: 1302601 (C4 (Web Text))

Max Activating Token Index: 957

Text #19

Max Range: 0.0290. Min Range: -0.0290

Max Act: 0.0208. Min Act: -0.0002

Data Index: 722998 (C4 (Web Text))

Max Activating Token Index: 757