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

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

Neuron 2273 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0407. Min Act: -0.0001

Data Index: 1050816 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0333. Min Act: -0.0001

Data Index: 671085 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0345. Min Act: -0.0001

Data Index: 140627 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0292. Min Act: -0.0001

Data Index: 637412 (C4 (Web Text))

Max Activating Token Index: 583

Text #4

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0270. Min Act: -0.0001

Data Index: 317428 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0254. Min Act: -0.0001

Data Index: 937448 (C4 (Web Text))

Max Activating Token Index: 272

Text #6

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0288. Min Act: -0.0001

Data Index: 352278 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0279. Min Act: -0.0001

Data Index: 184675 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0268. Min Act: -0.0001

Data Index: 261980 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0255. Min Act: -0.0001

Data Index: 153037 (C4 (Web Text))

Max Activating Token Index: 300

Text #10

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0231. Min Act: -0.0001

Data Index: 387880 (C4 (Web Text))

Max Activating Token Index: 706

Text #11

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0252. Min Act: -0.0001

Data Index: 127489 (C4 (Web Text))

Max Activating Token Index: 411

Text #12

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0243. Min Act: -0.0001

Data Index: 1639282 (Python Code)

Max Activating Token Index: 152

Text #13

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0233. Min Act: -0.0001

Data Index: 15924 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0247. Min Act: -0.0001

Data Index: 1009226 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0227. Min Act: -0.0000

Data Index: 541066 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0234. Min Act: -0.0001

Data Index: 933714 (C4 (Web Text))

Max Activating Token Index: 265

Text #17

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0264. Min Act: -0.0001

Data Index: 1263405 (C4 (Web Text))

Max Activating Token Index: 899

Text #18

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0242. Min Act: -0.0001

Data Index: 1635754 (Python Code)

Max Activating Token Index: 200

Text #19

Max Range: 0.0407. Min Range: -0.0407

Max Act: 0.0245. Min Act: -0.0001

Data Index: 1078757 (C4 (Web Text))

Max Activating Token Index: 320