Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3188 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0314. Min Act: -0.0000

Data Index: 762738 (C4 (Web Text))

Max Activating Token Index: 503

Text #1

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0279. Min Act: -0.0000

Data Index: 20691 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0303. Min Act: -0.0000

Data Index: 268367 (C4 (Web Text))

Max Activating Token Index: 76

Text #3

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0265. Min Act: -0.0000

Data Index: 1483279 (Python Code)

Max Activating Token Index: 851

Text #4

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0261. Min Act: -0.0000

Data Index: 805365 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0280. Min Act: -0.0000

Data Index: 248707 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0278. Min Act: -0.0000

Data Index: 937197 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0241. Min Act: -0.0000

Data Index: 688740 (C4 (Web Text))

Max Activating Token Index: 955

Text #8

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0272. Min Act: -0.0000

Data Index: 1424558 (Python Code)

Max Activating Token Index: 95

Text #9

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0288. Min Act: -0.0000

Data Index: 948318 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0261. Min Act: -0.0000

Data Index: 707832 (C4 (Web Text))

Max Activating Token Index: 282

Text #11

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0265. Min Act: -0.0000

Data Index: 536003 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0271. Min Act: -0.0000

Data Index: 9927 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0257. Min Act: -0.0000

Data Index: 575512 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0243. Min Act: -0.0000

Data Index: 284592 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0238. Min Act: -0.0000

Data Index: 446553 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0247. Min Act: -0.0000

Data Index: 1527737 (Python Code)

Max Activating Token Index: 527

Text #17

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0244. Min Act: -0.0000

Data Index: 1171001 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0235. Min Act: -0.0000

Data Index: 634273 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 0.0314. Min Range: -0.0314

Max Act: 0.0245. Min Act: -0.0000

Data Index: 1098796 (C4 (Web Text))

Max Activating Token Index: 423