Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2212 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0208. Min Act: -0.0002

Data Index: 176979 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0220. Min Act: -0.0002

Data Index: 1348065 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0194. Min Act: -0.0002

Data Index: 1276590 (C4 (Web Text))

Max Activating Token Index: 839

Text #3

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0202. Min Act: -0.0002

Data Index: 1054152 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0181. Min Act: -0.0002

Data Index: 1074827 (C4 (Web Text))

Max Activating Token Index: 199

Text #5

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0188. Min Act: -0.0002

Data Index: 929512 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0180. Min Act: -0.0002

Data Index: 23410 (C4 (Web Text))

Max Activating Token Index: 322

Text #7

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0182. Min Act: -0.0002

Data Index: 352785 (C4 (Web Text))

Max Activating Token Index: 386

Text #8

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0176. Min Act: -0.0002

Data Index: 797232 (C4 (Web Text))

Max Activating Token Index: 200

Text #9

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0164. Min Act: -0.0002

Data Index: 1572768 (Python Code)

Max Activating Token Index: 563

Text #10

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0170. Min Act: -0.0002

Data Index: 100506 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0170. Min Act: -0.0002

Data Index: 1408037 (Python Code)

Max Activating Token Index: 650

Text #12

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0159. Min Act: -0.0002

Data Index: 484909 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0154. Min Act: -0.0002

Data Index: 277112 (C4 (Web Text))

Max Activating Token Index: 365

Text #14

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0144. Min Act: -0.0002

Data Index: 660934 (C4 (Web Text))

Max Activating Token Index: 268

Text #15

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0157. Min Act: -0.0002

Data Index: 264903 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0151. Min Act: -0.0002

Data Index: 1147978 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0153. Min Act: -0.0002

Data Index: 445832 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0151. Min Act: -0.0002

Data Index: 1186315 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 0.0220. Min Range: -0.0220

Max Act: 0.0159. Min Act: -0.0002

Data Index: 249920 (C4 (Web Text))

Max Activating Token Index: 823