Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1122 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1358. Min Act: -0.0002

Data Index: 246875 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1372. Min Act: -0.0002

Data Index: 400258 (C4 (Web Text))

Max Activating Token Index: 709

Text #2

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1379. Min Act: -0.0002

Data Index: 901739 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1325. Min Act: -0.0002

Data Index: 1168659 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1225. Min Act: -0.0002

Data Index: 1156882 (C4 (Web Text))

Max Activating Token Index: 612

Text #5

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1213. Min Act: -0.0002

Data Index: 1349011 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1203. Min Act: -0.0002

Data Index: 1237094 (C4 (Web Text))

Max Activating Token Index: 963

Text #7

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1184. Min Act: -0.0002

Data Index: 627004 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1128. Min Act: -0.0002

Data Index: 1189172 (C4 (Web Text))

Max Activating Token Index: 955

Text #9

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1163. Min Act: -0.0002

Data Index: 1052776 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1121. Min Act: -0.0002

Data Index: 929872 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1111. Min Act: -0.0002

Data Index: 935185 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1095. Min Act: -0.0002

Data Index: 611873 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1087. Min Act: -0.0002

Data Index: 251562 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1048. Min Act: -0.0002

Data Index: 1314496 (C4 (Web Text))

Max Activating Token Index: 313

Text #15

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1073. Min Act: -0.0002

Data Index: 40233 (C4 (Web Text))

Max Activating Token Index: 118

Text #16

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1054. Min Act: -0.0002

Data Index: 962541 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1050. Min Act: -0.0002

Data Index: 19627 (C4 (Web Text))

Max Activating Token Index: 541

Text #18

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1041. Min Act: -0.0002

Data Index: 178 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.0999. Min Act: -0.0002

Data Index: 1224831 (C4 (Web Text))

Max Activating Token Index: 572