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

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

Neuron 5809 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: 0.0231. Min Range: -0.0231

Max Act: 0.0231. Min Act: -0.0002

Data Index: 1571433 (Python Code)

Max Activating Token Index: 532

Text #1

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0211. Min Act: -0.0002

Data Index: 1450751 (Python Code)

Max Activating Token Index: 878

Text #2

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0191. Min Act: -0.0002

Data Index: 1420816 (Python Code)

Max Activating Token Index: 303

Text #3

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0176. Min Act: -0.0002

Data Index: 1483952 (Python Code)

Max Activating Token Index: 286

Text #4

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0177. Min Act: -0.0002

Data Index: 1446391 (Python Code)

Max Activating Token Index: 671

Text #5

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0166. Min Act: -0.0002

Data Index: 1645489 (Python Code)

Max Activating Token Index: 305

Text #6

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0177. Min Act: -0.0002

Data Index: 1424715 (Python Code)

Max Activating Token Index: 265

Text #7

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0159. Min Act: -0.0002

Data Index: 563068 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0162. Min Act: -0.0002

Data Index: 1404258 (Python Code)

Max Activating Token Index: 752

Text #9

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0159. Min Act: -0.0002

Data Index: 1563777 (Python Code)

Max Activating Token Index: 361

Text #10

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0162. Min Act: -0.0002

Data Index: 752484 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0155. Min Act: -0.0002

Data Index: 1609153 (Python Code)

Max Activating Token Index: 401

Text #12

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0152. Min Act: -0.0002

Data Index: 1442537 (Python Code)

Max Activating Token Index: 597

Text #13

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0154. Min Act: -0.0002

Data Index: 377779 (C4 (Web Text))

Max Activating Token Index: 431

Text #14

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0150. Min Act: -0.0002

Data Index: 1469233 (Python Code)

Max Activating Token Index: 302

Text #15

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0149. Min Act: -0.0002

Data Index: 1599621 (Python Code)

Max Activating Token Index: 641

Text #16

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0152. Min Act: -0.0002

Data Index: 1350993 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0146. Min Act: -0.0002

Data Index: 1444532 (Python Code)

Max Activating Token Index: 210

Text #18

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0138. Min Act: -0.0002

Data Index: 254700 (C4 (Web Text))

Max Activating Token Index: 655

Text #19

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0143. Min Act: -0.0002

Data Index: 1652826 (Python Code)

Max Activating Token Index: 227