Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 31 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1401. Min Act: -0.0003

Data Index: 693369 (C4 (Web Text))

Max Activating Token Index: 662

Text #1

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1321. Min Act: -0.0003

Data Index: 1057758 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1409. Min Act: -0.0003

Data Index: 821712 (C4 (Web Text))

Max Activating Token Index: 523

Text #3

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1322. Min Act: -0.0003

Data Index: 562326 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1258. Min Act: -0.0003

Data Index: 82833 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1361. Min Act: -0.0003

Data Index: 1248584 (C4 (Web Text))

Max Activating Token Index: 230

Text #6

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1345. Min Act: -0.0003

Data Index: 960755 (C4 (Web Text))

Max Activating Token Index: 566

Text #7

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1340. Min Act: -0.0003

Data Index: 44239 (C4 (Web Text))

Max Activating Token Index: 333

Text #8

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1236. Min Act: -0.0003

Data Index: 123366 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1192. Min Act: -0.0003

Data Index: 459904 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1163. Min Act: -0.0003

Data Index: 521982 (C4 (Web Text))

Max Activating Token Index: 671

Text #11

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1247. Min Act: -0.0003

Data Index: 995035 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1277. Min Act: -0.0003

Data Index: 901799 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1152. Min Act: -0.0003

Data Index: 1175379 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1132. Min Act: -0.0003

Data Index: 344415 (C4 (Web Text))

Max Activating Token Index: 625

Text #15

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1181. Min Act: -0.0003

Data Index: 252860 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1090. Min Act: -0.0003

Data Index: 1066627 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1221. Min Act: -0.0003

Data Index: 344340 (C4 (Web Text))

Max Activating Token Index: 666

Text #18

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1256. Min Act: -0.0003

Data Index: 920278 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1151. Min Act: -0.0003

Data Index: 541821 (C4 (Web Text))

Max Activating Token Index: 281