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

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

Neuron 1880 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: 0.1314. Min Range: -0.1314

Max Act: 0.1314. Min Act: -0.0000

Data Index: 172834 (C4 (Web Text))

Max Activating Token Index: 408

Text #1

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1312. Min Act: -0.0002

Data Index: 764810 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1297. Min Act: -0.0002

Data Index: 667127 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1277. Min Act: -0.0002

Data Index: 144925 (C4 (Web Text))

Max Activating Token Index: 358

Text #4

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1249. Min Act: -0.0002

Data Index: 585150 (C4 (Web Text))

Max Activating Token Index: 378

Text #5

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1198. Min Act: -0.0000

Data Index: 1277527 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1246. Min Act: -0.0002

Data Index: 640873 (C4 (Web Text))

Max Activating Token Index: 921

Text #7

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1167. Min Act: -0.0000

Data Index: 117951 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1150. Min Act: -0.0000

Data Index: 1345391 (C4 (Web Text))

Max Activating Token Index: 548

Text #9

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1156. Min Act: -0.0002

Data Index: 812237 (C4 (Web Text))

Max Activating Token Index: 774

Text #10

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1129. Min Act: -0.0002

Data Index: 986017 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1142. Min Act: -0.0002

Data Index: 541352 (C4 (Web Text))

Max Activating Token Index: 564

Text #12

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1097. Min Act: -0.0002

Data Index: 347076 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1181. Min Act: -0.0000

Data Index: 1146350 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1053. Min Act: -0.0002

Data Index: 1072384 (C4 (Web Text))

Max Activating Token Index: 673

Text #15

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1110. Min Act: -0.0002

Data Index: 209464 (C4 (Web Text))

Max Activating Token Index: 334

Text #16

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1162. Min Act: -0.0001

Data Index: 1136504 (C4 (Web Text))

Max Activating Token Index: 260

Text #17

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1123. Min Act: -0.0001

Data Index: 933140 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1114. Min Act: -0.0002

Data Index: 469064 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 0.1314. Min Range: -0.1314

Max Act: 0.1111. Min Act: -0.0002

Data Index: 1195494 (C4 (Web Text))

Max Activating Token Index: 383