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

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

Neuron 1531 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1453. Min Act: -0.0005

Data Index: 207166 (C4 (Web Text))

Max Activating Token Index: 844

Text #1

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1405. Min Act: -0.0005

Data Index: 943337 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1298. Min Act: -0.0005

Data Index: 284057 (C4 (Web Text))

Max Activating Token Index: 646

Text #3

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1242. Min Act: -0.0005

Data Index: 1252154 (C4 (Web Text))

Max Activating Token Index: 771

Text #4

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1297. Min Act: -0.0005

Data Index: 391986 (C4 (Web Text))

Max Activating Token Index: 110

Text #5

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1294. Min Act: -0.0005

Data Index: 1228439 (C4 (Web Text))

Max Activating Token Index: 1000

Text #6

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1230. Min Act: -0.0005

Data Index: 469327 (C4 (Web Text))

Max Activating Token Index: 349

Text #7

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1217. Min Act: -0.0005

Data Index: 92786 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1197. Min Act: -0.0005

Data Index: 236372 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1220. Min Act: -0.0005

Data Index: 646137 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1232. Min Act: -0.0005

Data Index: 1014094 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1169. Min Act: -0.0005

Data Index: 1342014 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1179. Min Act: -0.0005

Data Index: 563776 (C4 (Web Text))

Max Activating Token Index: 920

Text #13

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1204. Min Act: -0.0005

Data Index: 1109697 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1172. Min Act: -0.0005

Data Index: 563297 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1199. Min Act: -0.0005

Data Index: 32146 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1038. Min Act: -0.0005

Data Index: 491168 (C4 (Web Text))

Max Activating Token Index: 699

Text #17

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1160. Min Act: -0.0005

Data Index: 128259 (C4 (Web Text))

Max Activating Token Index: 112

Text #18

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1187. Min Act: -0.0005

Data Index: 826788 (C4 (Web Text))

Max Activating Token Index: 757

Text #19

Max Range: 0.1453. Min Range: -0.1453

Max Act: 0.1162. Min Act: -0.0005

Data Index: 849292 (C4 (Web Text))

Max Activating Token Index: 573