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

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

Neuron 2343 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1376. Min Act: -0.0000

Data Index: 256131 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1336. Min Act: -0.0001

Data Index: 139384 (C4 (Web Text))

Max Activating Token Index: 504

Text #2

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1222. Min Act: -0.0001

Data Index: 271927 (C4 (Web Text))

Max Activating Token Index: 797

Text #3

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1347. Min Act: -0.0001

Data Index: 1320476 (C4 (Web Text))

Max Activating Token Index: 840

Text #4

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1229. Min Act: -0.0000

Data Index: 488764 (C4 (Web Text))

Max Activating Token Index: 636

Text #5

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1232. Min Act: -0.0000

Data Index: 130713 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1277. Min Act: -0.0001

Data Index: 1231585 (C4 (Web Text))

Max Activating Token Index: 582

Text #7

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1307. Min Act: -0.0001

Data Index: 428858 (C4 (Web Text))

Max Activating Token Index: 617

Text #8

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1240. Min Act: -0.0001

Data Index: 118432 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1245. Min Act: -0.0001

Data Index: 1331177 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1187. Min Act: -0.0000

Data Index: 28758 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1213. Min Act: -0.0000

Data Index: 292893 (C4 (Web Text))

Max Activating Token Index: 890

Text #12

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1188. Min Act: -0.0001

Data Index: 1062829 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1147. Min Act: -0.0001

Data Index: 970503 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1224. Min Act: -0.0000

Data Index: 1325563 (C4 (Web Text))

Max Activating Token Index: 72

Text #15

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1138. Min Act: -0.0001

Data Index: 12296 (C4 (Web Text))

Max Activating Token Index: 18

Text #16

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1178. Min Act: -0.0001

Data Index: 1244177 (C4 (Web Text))

Max Activating Token Index: 425

Text #17

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1080. Min Act: -0.0001

Data Index: 1048071 (C4 (Web Text))

Max Activating Token Index: 240

Text #18

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1175. Min Act: -0.0001

Data Index: 798579 (C4 (Web Text))

Max Activating Token Index: 82

Text #19

Max Range: 0.1376. Min Range: -0.1376

Max Act: 0.1132. Min Act: -0.0001

Data Index: 511632 (C4 (Web Text))

Max Activating Token Index: 624