Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 191 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1400. Min Act: -0.0002

Data Index: 831238 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1379. Min Act: -0.0002

Data Index: 740681 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1305. Min Act: -0.0002

Data Index: 537980 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1423. Min Act: -0.0002

Data Index: 620312 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1350. Min Act: -0.0002

Data Index: 853572 (C4 (Web Text))

Max Activating Token Index: 357

Text #5

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1381. Min Act: -0.0002

Data Index: 1059656 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1428. Min Act: -0.0002

Data Index: 447847 (C4 (Web Text))

Max Activating Token Index: 237

Text #7

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1290. Min Act: -0.0002

Data Index: 679590 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1280. Min Act: -0.0002

Data Index: 439636 (C4 (Web Text))

Max Activating Token Index: 141

Text #9

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1354. Min Act: -0.0002

Data Index: 304837 (C4 (Web Text))

Max Activating Token Index: 1018

Text #10

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1362. Min Act: -0.0002

Data Index: 507481 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1265. Min Act: -0.0002

Data Index: 17387 (C4 (Web Text))

Max Activating Token Index: 367

Text #12

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1265. Min Act: -0.0002

Data Index: 700901 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1298. Min Act: -0.0002

Data Index: 856387 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1267. Min Act: -0.0002

Data Index: 991351 (C4 (Web Text))

Max Activating Token Index: 373

Text #15

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1286. Min Act: -0.0002

Data Index: 1315183 (C4 (Web Text))

Max Activating Token Index: 892

Text #16

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1259. Min Act: -0.0002

Data Index: 612432 (C4 (Web Text))

Max Activating Token Index: 268

Text #17

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1242. Min Act: -0.0002

Data Index: 371037 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1193. Min Act: -0.0002

Data Index: 346901 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1224. Min Act: -0.0002

Data Index: 33266 (C4 (Web Text))

Max Activating Token Index: 530