Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 28 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0429. Min Act: -0.0002

Data Index: 1147138 (C4 (Web Text))

Max Activating Token Index: 749

Text #1

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0391. Min Act: -0.0002

Data Index: 362202 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0347. Min Act: -0.0002

Data Index: 882875 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0334. Min Act: -0.0002

Data Index: 1033226 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0328. Min Act: -0.0002

Data Index: 1334316 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0342. Min Act: -0.0002

Data Index: 1071297 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0324. Min Act: -0.0002

Data Index: 169068 (C4 (Web Text))

Max Activating Token Index: 553

Text #7

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0319. Min Act: -0.0002

Data Index: 941181 (C4 (Web Text))

Max Activating Token Index: 909

Text #8

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0327. Min Act: -0.0002

Data Index: 1016286 (C4 (Web Text))

Max Activating Token Index: 399

Text #9

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0316. Min Act: -0.0002

Data Index: 1547449 (Python Code)

Max Activating Token Index: 673

Text #10

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0322. Min Act: -0.0002

Data Index: 370748 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0313. Min Act: -0.0002

Data Index: 446361 (C4 (Web Text))

Max Activating Token Index: 103

Text #12

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0305. Min Act: -0.0002

Data Index: 715005 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0308. Min Act: -0.0002

Data Index: 1241947 (C4 (Web Text))

Max Activating Token Index: 19

Text #14

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0309. Min Act: -0.0002

Data Index: 204743 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0304. Min Act: -0.0002

Data Index: 1312812 (C4 (Web Text))

Max Activating Token Index: 573

Text #16

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0313. Min Act: -0.0002

Data Index: 207247 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0296. Min Act: -0.0002

Data Index: 106061 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0308. Min Act: -0.0002

Data Index: 316732 (C4 (Web Text))

Max Activating Token Index: 646

Text #19

Max Range: 0.0429. Min Range: -0.0429

Max Act: 0.0286. Min Act: -0.0002

Data Index: 911194 (C4 (Web Text))

Max Activating Token Index: 752