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

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

Neuron 323 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0412. Min Act: -0.0001

Data Index: 948126 (C4 (Web Text))

Max Activating Token Index: 490

Text #1

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0386. Min Act: -0.0001

Data Index: 1427945 (Python Code)

Max Activating Token Index: 379

Text #2

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0376. Min Act: -0.0001

Data Index: 932195 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0345. Min Act: -0.0001

Data Index: 1543468 (Python Code)

Max Activating Token Index: 213

Text #4

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0340. Min Act: -0.0001

Data Index: 1317922 (C4 (Web Text))

Max Activating Token Index: 195

Text #5

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0313. Min Act: -0.0001

Data Index: 1637831 (Python Code)

Max Activating Token Index: 388

Text #6

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0305. Min Act: -0.0001

Data Index: 633534 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0274. Min Act: -0.0001

Data Index: 10903 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0271. Min Act: -0.0001

Data Index: 511014 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0257. Min Act: -0.0001

Data Index: 1396435 (Python Code)

Max Activating Token Index: 698

Text #10

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0275. Min Act: -0.0001

Data Index: 204790 (C4 (Web Text))

Max Activating Token Index: 742

Text #11

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0259. Min Act: -0.0001

Data Index: 311461 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0255. Min Act: -0.0001

Data Index: 571698 (C4 (Web Text))

Max Activating Token Index: 863

Text #13

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0264. Min Act: -0.0001

Data Index: 1225967 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0249. Min Act: -0.0001

Data Index: 481138 (C4 (Web Text))

Max Activating Token Index: 431

Text #15

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0259. Min Act: -0.0002

Data Index: 919398 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0253. Min Act: -0.0001

Data Index: 931085 (C4 (Web Text))

Max Activating Token Index: 242

Text #17

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0251. Min Act: -0.0001

Data Index: 1445604 (Python Code)

Max Activating Token Index: 821

Text #18

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0243. Min Act: -0.0001

Data Index: 1636472 (Python Code)

Max Activating Token Index: 851

Text #19

Max Range: 0.0412. Min Range: -0.0412

Max Act: 0.0241. Min Act: -0.0001

Data Index: 532523 (C4 (Web Text))

Max Activating Token Index: 324