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

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

Neuron 2250 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1607. Min Act: -0.0001

Data Index: 279237 (C4 (Web Text))

Max Activating Token Index: 259

Text #1

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1374. Min Act: -0.0001

Data Index: 51284 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1349. Min Act: -0.0001

Data Index: 423630 (C4 (Web Text))

Max Activating Token Index: 998

Text #3

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1273. Min Act: -0.0001

Data Index: 346400 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1248. Min Act: -0.0001

Data Index: 1247250 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1345. Min Act: -0.0001

Data Index: 133903 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1214. Min Act: -0.0001

Data Index: 914626 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1245. Min Act: -0.0001

Data Index: 690956 (C4 (Web Text))

Max Activating Token Index: 370

Text #8

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1284. Min Act: -0.0001

Data Index: 355132 (C4 (Web Text))

Max Activating Token Index: 312

Text #9

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1216. Min Act: -0.0001

Data Index: 74297 (C4 (Web Text))

Max Activating Token Index: 185

Text #10

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1235. Min Act: -0.0001

Data Index: 1233757 (C4 (Web Text))

Max Activating Token Index: 951

Text #11

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1183. Min Act: -0.0001

Data Index: 953801 (C4 (Web Text))

Max Activating Token Index: 524

Text #12

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1200. Min Act: -0.0001

Data Index: 642033 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1134. Min Act: -0.0001

Data Index: 437380 (C4 (Web Text))

Max Activating Token Index: 745

Text #14

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1217. Min Act: -0.0001

Data Index: 662504 (C4 (Web Text))

Max Activating Token Index: 234

Text #15

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1189. Min Act: -0.0001

Data Index: 1000931 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1067. Min Act: -0.0001

Data Index: 853541 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1027. Min Act: -0.0001

Data Index: 1202551 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1051. Min Act: -0.0001

Data Index: 484713 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 0.1607. Min Range: -0.1607

Max Act: 0.1088. Min Act: -0.0001

Data Index: 333276 (C4 (Web Text))

Max Activating Token Index: 340