Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3338 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0200. Min Act: -0.0003

Data Index: 594062 (C4 (Web Text))

Max Activating Token Index: 278

Text #1

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0184. Min Act: -0.0002

Data Index: 231111 (C4 (Web Text))

Max Activating Token Index: 216

Text #2

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0178. Min Act: -0.0002

Data Index: 1355296 (C4 (Web Text))

Max Activating Token Index: 301

Text #3

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0174. Min Act: -0.0002

Data Index: 726212 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0174. Min Act: -0.0002

Data Index: 610890 (C4 (Web Text))

Max Activating Token Index: 259

Text #5

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0170. Min Act: -0.0003

Data Index: 212017 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0166. Min Act: -0.0002

Data Index: 1212862 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0164. Min Act: -0.0003

Data Index: 298347 (C4 (Web Text))

Max Activating Token Index: 315

Text #8

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0163. Min Act: -0.0002

Data Index: 221380 (C4 (Web Text))

Max Activating Token Index: 594

Text #9

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0159. Min Act: -0.0003

Data Index: 554347 (C4 (Web Text))

Max Activating Token Index: 461

Text #10

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0154. Min Act: -0.0002

Data Index: 143032 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0154. Min Act: -0.0002

Data Index: 1037549 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0153. Min Act: -0.0002

Data Index: 989905 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0153. Min Act: -0.0002

Data Index: 800010 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0151. Min Act: -0.0002

Data Index: 376154 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0150. Min Act: -0.0002

Data Index: 15356 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0153. Min Act: -0.0002

Data Index: 823647 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0149. Min Act: -0.0003

Data Index: 640173 (C4 (Web Text))

Max Activating Token Index: 42

Text #18

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0146. Min Act: -0.0002

Data Index: 901059 (C4 (Web Text))

Max Activating Token Index: 740

Text #19

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0143. Min Act: -0.0002

Data Index: 743102 (C4 (Web Text))

Max Activating Token Index: 101