Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3457 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1860. Min Act: -0.0001

Data Index: 429405 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1587. Min Act: -0.0000

Data Index: 811644 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1401. Min Act: -0.0000

Data Index: 38024 (C4 (Web Text))

Max Activating Token Index: 361

Text #3

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1345. Min Act: -0.0001

Data Index: 642906 (C4 (Web Text))

Max Activating Token Index: 654

Text #4

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1328. Min Act: -0.0000

Data Index: 154855 (C4 (Web Text))

Max Activating Token Index: 576

Text #5

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1317. Min Act: 0.0000

Data Index: 956451 (C4 (Web Text))

Max Activating Token Index: 975

Text #6

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1352. Min Act: -0.0000

Data Index: 1132444 (C4 (Web Text))

Max Activating Token Index: 477

Text #7

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1349. Min Act: -0.0000

Data Index: 626279 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1287. Min Act: -0.0000

Data Index: 47670 (C4 (Web Text))

Max Activating Token Index: 294

Text #9

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1224. Min Act: -0.0000

Data Index: 808953 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1224. Min Act: -0.0000

Data Index: 375598 (C4 (Web Text))

Max Activating Token Index: 227

Text #11

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1274. Min Act: -0.0000

Data Index: 702516 (C4 (Web Text))

Max Activating Token Index: 282

Text #12

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1234. Min Act: -0.0000

Data Index: 168998 (C4 (Web Text))

Max Activating Token Index: 897

Text #13

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1191. Min Act: -0.0001

Data Index: 269243 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1195. Min Act: -0.0000

Data Index: 1147514 (C4 (Web Text))

Max Activating Token Index: 957

Text #15

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1191. Min Act: -0.0000

Data Index: 1339269 (C4 (Web Text))

Max Activating Token Index: 637

Text #16

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1252. Min Act: -0.0000

Data Index: 674280 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1210. Min Act: -0.0001

Data Index: 391255 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1206. Min Act: -0.0000

Data Index: 562441 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 0.1860. Min Range: -0.1860

Max Act: 0.1169. Min Act: -0.0001

Data Index: 834228 (C4 (Web Text))

Max Activating Token Index: 304