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

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

Neuron 2561 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0216. Min Act: -0.0004

Data Index: 120880 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0219. Min Act: -0.0004

Data Index: 363188 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0191. Min Act: -0.0004

Data Index: 1639708 (Python Code)

Max Activating Token Index: 312

Text #3

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0189. Min Act: -0.0004

Data Index: 1440691 (Python Code)

Max Activating Token Index: 327

Text #4

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0189. Min Act: -0.0004

Data Index: 10509 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0177. Min Act: -0.0004

Data Index: 1518951 (Python Code)

Max Activating Token Index: 702

Text #6

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0198. Min Act: -0.0004

Data Index: 1596464 (Python Code)

Max Activating Token Index: 555

Text #7

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0180. Min Act: -0.0004

Data Index: 1283475 (C4 (Web Text))

Max Activating Token Index: 310

Text #8

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0180. Min Act: -0.0004

Data Index: 217315 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0146. Min Act: -0.0004

Data Index: 1089304 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0190. Min Act: -0.0004

Data Index: 1602684 (Python Code)

Max Activating Token Index: 153

Text #11

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0171. Min Act: -0.0004

Data Index: 1365661 (Python Code)

Max Activating Token Index: 575

Text #12

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0174. Min Act: -0.0004

Data Index: 1261486 (C4 (Web Text))

Max Activating Token Index: 789

Text #13

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0172. Min Act: -0.0004

Data Index: 59049 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0164. Min Act: -0.0004

Data Index: 1368397 (Python Code)

Max Activating Token Index: 283

Text #15

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0175. Min Act: -0.0004

Data Index: 716362 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0189. Min Act: -0.0004

Data Index: 1656253 (Python Code)

Max Activating Token Index: 902

Text #17

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0175. Min Act: -0.0004

Data Index: 1481065 (Python Code)

Max Activating Token Index: 541

Text #18

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0190. Min Act: -0.0004

Data Index: 1622451 (Python Code)

Max Activating Token Index: 893

Text #19

Max Range: 0.0219. Min Range: -0.0219

Max Act: 0.0193. Min Act: -0.0004

Data Index: 1555973 (Python Code)

Max Activating Token Index: 188