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

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

Neuron 630 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: 0.1715. Min Range: -0.1715

Max Act: 0.1715. Min Act: -0.0001

Data Index: 1237989 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1415. Min Act: -0.0002

Data Index: 1141595 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1321. Min Act: -0.0002

Data Index: 234624 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1320. Min Act: -0.0001

Data Index: 857010 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1397. Min Act: -0.0002

Data Index: 1118512 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1254. Min Act: -0.0001

Data Index: 815506 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1281. Min Act: -0.0002

Data Index: 695001 (C4 (Web Text))

Max Activating Token Index: 183

Text #7

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1209. Min Act: -0.0002

Data Index: 1019201 (C4 (Web Text))

Max Activating Token Index: 803

Text #8

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1308. Min Act: -0.0001

Data Index: 339767 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1289. Min Act: -0.0000

Data Index: 990384 (C4 (Web Text))

Max Activating Token Index: 770

Text #10

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1227. Min Act: -0.0002

Data Index: 1231210 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1206. Min Act: -0.0002

Data Index: 115626 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1213. Min Act: -0.0002

Data Index: 297115 (C4 (Web Text))

Max Activating Token Index: 824

Text #13

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1229. Min Act: -0.0002

Data Index: 559286 (C4 (Web Text))

Max Activating Token Index: 121

Text #14

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1271. Min Act: -0.0002

Data Index: 1267639 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1197. Min Act: -0.0001

Data Index: 1128937 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1236. Min Act: -0.0002

Data Index: 257886 (C4 (Web Text))

Max Activating Token Index: 344

Text #17

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1235. Min Act: -0.0002

Data Index: 635179 (C4 (Web Text))

Max Activating Token Index: 554

Text #18

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1164. Min Act: -0.0002

Data Index: 1225508 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 0.1715. Min Range: -0.1715

Max Act: 0.1156. Min Act: -0.0002

Data Index: 599744 (C4 (Web Text))

Max Activating Token Index: 463