Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 363 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0319. Min Act: -0.0003

Data Index: 1423584 (Python Code)

Max Activating Token Index: 6

Text #1

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0319. Min Act: -0.0003

Data Index: 1373439 (Python Code)

Max Activating Token Index: 6

Text #2

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0310. Min Act: -0.0004

Data Index: 1236441 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0312. Min Act: -0.0003

Data Index: 378197 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0295. Min Act: -0.0003

Data Index: 191750 (C4 (Web Text))

Max Activating Token Index: 348

Text #5

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0300. Min Act: -0.0003

Data Index: 1020004 (C4 (Web Text))

Max Activating Token Index: 478

Text #6

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0308. Min Act: -0.0003

Data Index: 357396 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0302. Min Act: -0.0004

Data Index: 512560 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0301. Min Act: -0.0004

Data Index: 1027567 (C4 (Web Text))

Max Activating Token Index: 703

Text #9

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0285. Min Act: -0.0003

Data Index: 1264211 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0287. Min Act: -0.0003

Data Index: 109137 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0283. Min Act: -0.0003

Data Index: 322306 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0289. Min Act: -0.0004

Data Index: 687687 (C4 (Web Text))

Max Activating Token Index: 801

Text #13

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0282. Min Act: -0.0003

Data Index: 459166 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0289. Min Act: -0.0003

Data Index: 61652 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0294. Min Act: -0.0004

Data Index: 997313 (C4 (Web Text))

Max Activating Token Index: 712

Text #16

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0291. Min Act: -0.0004

Data Index: 720392 (C4 (Web Text))

Max Activating Token Index: 259

Text #17

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0280. Min Act: -0.0003

Data Index: 1484400 (Python Code)

Max Activating Token Index: 8

Text #18

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0292. Min Act: -0.0003

Data Index: 648940 (C4 (Web Text))

Max Activating Token Index: 447

Text #19

Max Range: 0.0319. Min Range: -0.0319

Max Act: 0.0286. Min Act: -0.0003

Data Index: 1563395 (Python Code)

Max Activating Token Index: 5