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

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

Neuron 1533 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1556. Min Act: -0.0002

Data Index: 864805 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1357. Min Act: -0.0002

Data Index: 670586 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1288. Min Act: -0.0002

Data Index: 626049 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1349. Min Act: -0.0002

Data Index: 887893 (C4 (Web Text))

Max Activating Token Index: 199

Text #4

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1272. Min Act: -0.0002

Data Index: 917836 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1295. Min Act: -0.0002

Data Index: 925335 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1451. Min Act: -0.0002

Data Index: 1203723 (C4 (Web Text))

Max Activating Token Index: 853

Text #7

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1369. Min Act: -0.0002

Data Index: 1237028 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1271. Min Act: -0.0002

Data Index: 42766 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1226. Min Act: -0.0002

Data Index: 26778 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1328. Min Act: -0.0002

Data Index: 884287 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1153. Min Act: -0.0002

Data Index: 1055461 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1293. Min Act: -0.0002

Data Index: 417345 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1351. Min Act: -0.0002

Data Index: 596630 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1327. Min Act: -0.0002

Data Index: 1280605 (C4 (Web Text))

Max Activating Token Index: 21

Text #15

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1283. Min Act: -0.0003

Data Index: 1130971 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1244. Min Act: -0.0002

Data Index: 716090 (C4 (Web Text))

Max Activating Token Index: 382

Text #17

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1344. Min Act: -0.0002

Data Index: 619270 (C4 (Web Text))

Max Activating Token Index: 230

Text #18

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1318. Min Act: -0.0002

Data Index: 47029 (C4 (Web Text))

Max Activating Token Index: 304

Text #19

Max Range: 0.1556. Min Range: -0.1556

Max Act: 0.1330. Min Act: -0.0002

Data Index: 629521 (C4 (Web Text))

Max Activating Token Index: 67