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

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

Neuron 6110 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.2367. Min Act: -0.0002

Data Index: 419322 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.2337. Min Act: -0.0002

Data Index: 1548048 (Python Code)

Max Activating Token Index: 778

Text #2

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.2311. Min Act: -0.0002

Data Index: 1065434 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.2259. Min Act: -0.0002

Data Index: 286903 (C4 (Web Text))

Max Activating Token Index: 701

Text #4

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.2209. Min Act: -0.0002

Data Index: 708285 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.2208. Min Act: -0.0002

Data Index: 238103 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.2220. Min Act: -0.0002

Data Index: 144945 (C4 (Web Text))

Max Activating Token Index: 728

Text #7

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.2172. Min Act: -0.0002

Data Index: 516739 (C4 (Web Text))

Max Activating Token Index: 749

Text #8

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.2165. Min Act: -0.0002

Data Index: 886990 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.2156. Min Act: -0.0002

Data Index: 670187 (C4 (Web Text))

Max Activating Token Index: 727

Text #10

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.2112. Min Act: -0.0002

Data Index: 668965 (C4 (Web Text))

Max Activating Token Index: 637

Text #11

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.2094. Min Act: -0.0002

Data Index: 890001 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.2113. Min Act: -0.0002

Data Index: 904951 (C4 (Web Text))

Max Activating Token Index: 22

Text #13

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.2112. Min Act: -0.0002

Data Index: 160663 (C4 (Web Text))

Max Activating Token Index: 323

Text #14

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.2175. Min Act: -0.0002

Data Index: 729194 (C4 (Web Text))

Max Activating Token Index: 521

Text #15

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.2120. Min Act: -0.0002

Data Index: 926909 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.2102. Min Act: -0.0002

Data Index: 1520995 (Python Code)

Max Activating Token Index: 788

Text #17

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.2089. Min Act: -0.0002

Data Index: 536997 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.2095. Min Act: -0.0002

Data Index: 316547 (C4 (Web Text))

Max Activating Token Index: 870

Text #19

Max Range: 0.2367. Min Range: -0.2367

Max Act: 0.2094. Min Act: -0.0002

Data Index: 601330 (C4 (Web Text))

Max Activating Token Index: 245