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

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

Neuron 496 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1642. Min Act: -0.0001

Data Index: 720271 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1431. Min Act: -0.0001

Data Index: 195915 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1461. Min Act: -0.0000

Data Index: 333323 (C4 (Web Text))

Max Activating Token Index: 455

Text #3

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1325. Min Act: -0.0000

Data Index: 1179904 (C4 (Web Text))

Max Activating Token Index: 927

Text #4

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1330. Min Act: -0.0000

Data Index: 251675 (C4 (Web Text))

Max Activating Token Index: 995

Text #5

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1308. Min Act: -0.0000

Data Index: 775124 (C4 (Web Text))

Max Activating Token Index: 492

Text #6

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1190. Min Act: -0.0001

Data Index: 403350 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1283. Min Act: -0.0001

Data Index: 1229591 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1278. Min Act: -0.0001

Data Index: 161790 (C4 (Web Text))

Max Activating Token Index: 134

Text #9

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1269. Min Act: -0.0000

Data Index: 89355 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1215. Min Act: -0.0000

Data Index: 742201 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1214. Min Act: -0.0001

Data Index: 1321721 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1305. Min Act: -0.0001

Data Index: 277494 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1239. Min Act: -0.0000

Data Index: 102028 (C4 (Web Text))

Max Activating Token Index: 828

Text #14

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1241. Min Act: -0.0000

Data Index: 793669 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1266. Min Act: -0.0000

Data Index: 494223 (C4 (Web Text))

Max Activating Token Index: 411

Text #16

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1222. Min Act: -0.0001

Data Index: 40449 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1219. Min Act: -0.0001

Data Index: 1109069 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1211. Min Act: -0.0000

Data Index: 330599 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1204. Min Act: -0.0000

Data Index: 756614 (C4 (Web Text))

Max Activating Token Index: 587