Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2759 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2397. Min Range: -0.2397

Max Act: 0.2397. Min Act: -0.0001

Data Index: 35194 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 0.2397. Min Range: -0.2397

Max Act: 0.2194. Min Act: -0.0000

Data Index: 758507 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 0.2397. Min Range: -0.2397

Max Act: 0.2176. Min Act: -0.0000

Data Index: 952678 (C4 (Web Text))

Max Activating Token Index: 890

Text #3

Max Range: 0.2397. Min Range: -0.2397

Max Act: 0.1755. Min Act: -0.0000

Data Index: 1281360 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 0.2397. Min Range: -0.2397

Max Act: 0.1798. Min Act: -0.0000

Data Index: 1207596 (C4 (Web Text))

Max Activating Token Index: 268

Text #5

Max Range: 0.2397. Min Range: -0.2397

Max Act: 0.1398. Min Act: -0.0000

Data Index: 96770 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 0.2397. Min Range: -0.2397

Max Act: 0.1532. Min Act: -0.0000

Data Index: 833229 (C4 (Web Text))

Max Activating Token Index: 588

Text #7

Max Range: 0.2397. Min Range: -0.2397

Max Act: 0.1560. Min Act: -0.0000

Data Index: 937681 (C4 (Web Text))

Max Activating Token Index: 421

Text #8

Max Range: 0.2397. Min Range: -0.2397

Max Act: 0.1445. Min Act: -0.0000

Data Index: 795083 (C4 (Web Text))

Max Activating Token Index: 542

Text #9

Max Range: 0.2397. Min Range: -0.2397

Max Act: 0.1462. Min Act: -0.0000

Data Index: 544255 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 0.2397. Min Range: -0.2397

Max Act: 0.1394. Min Act: -0.0000

Data Index: 37676 (C4 (Web Text))

Max Activating Token Index: 647

Text #11

Max Range: 0.2397. Min Range: -0.2397

Max Act: 0.1395. Min Act: -0.0000

Data Index: 787800 (C4 (Web Text))

Max Activating Token Index: 385

Text #12

Max Range: 0.2397. Min Range: -0.2397

Max Act: 0.1299. Min Act: -0.0001

Data Index: 361212 (C4 (Web Text))

Max Activating Token Index: 445

Text #13

Max Range: 0.2397. Min Range: -0.2397

Max Act: 0.1288. Min Act: -0.0000

Data Index: 778072 (C4 (Web Text))

Max Activating Token Index: 408

Text #14

Max Range: 0.2397. Min Range: -0.2397

Max Act: 0.1218. Min Act: -0.0000

Data Index: 565371 (C4 (Web Text))

Max Activating Token Index: 613

Text #15

Max Range: 0.2397. Min Range: -0.2397

Max Act: 0.1280. Min Act: -0.0000

Data Index: 803814 (C4 (Web Text))

Max Activating Token Index: 859

Text #16

Max Range: 0.2397. Min Range: -0.2397

Max Act: 0.1287. Min Act: -0.0000

Data Index: 471018 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 0.2397. Min Range: -0.2397

Max Act: 0.1184. Min Act: -0.0000

Data Index: 709237 (C4 (Web Text))

Max Activating Token Index: 701

Text #18

Max Range: 0.2397. Min Range: -0.2397

Max Act: 0.1179. Min Act: -0.0000

Data Index: 1229101 (C4 (Web Text))

Max Activating Token Index: 356

Text #19

Max Range: 0.2397. Min Range: -0.2397

Max Act: 0.1217. Min Act: -0.0000

Data Index: 1153406 (C4 (Web Text))

Max Activating Token Index: 282