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

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

Neuron 3028 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: 0.0214. Min Range: -0.0214

Max Act: 0.0214. Min Act: -0.0002

Data Index: 1634408 (Python Code)

Max Activating Token Index: 1

Text #1

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0180. Min Act: -0.0003

Data Index: 197289 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0177. Min Act: -0.0002

Data Index: 1501998 (Python Code)

Max Activating Token Index: 26

Text #3

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0177. Min Act: -0.0003

Data Index: 405894 (C4 (Web Text))

Max Activating Token Index: 447

Text #4

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0176. Min Act: -0.0003

Data Index: 148411 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0176. Min Act: -0.0002

Data Index: 1556555 (Python Code)

Max Activating Token Index: 1

Text #6

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0176. Min Act: -0.0002

Data Index: 1615624 (Python Code)

Max Activating Token Index: 1

Text #7

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0175. Min Act: -0.0002

Data Index: 1644322 (Python Code)

Max Activating Token Index: 1

Text #8

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0174. Min Act: -0.0002

Data Index: 1433734 (Python Code)

Max Activating Token Index: 11

Text #9

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0173. Min Act: -0.0002

Data Index: 102371 (C4 (Web Text))

Max Activating Token Index: 1

Text #10

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0173. Min Act: -0.0002

Data Index: 1606575 (Python Code)

Max Activating Token Index: 1

Text #11

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0173. Min Act: -0.0002

Data Index: 1397041 (Python Code)

Max Activating Token Index: 1

Text #12

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0173. Min Act: -0.0002

Data Index: 1653881 (Python Code)

Max Activating Token Index: 1

Text #13

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0173. Min Act: -0.0002

Data Index: 1567533 (Python Code)

Max Activating Token Index: 1

Text #14

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0173. Min Act: -0.0002

Data Index: 1368997 (Python Code)

Max Activating Token Index: 1

Text #15

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0173. Min Act: -0.0002

Data Index: 1423364 (Python Code)

Max Activating Token Index: 1

Text #16

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0173. Min Act: -0.0003

Data Index: 1196303 (C4 (Web Text))

Max Activating Token Index: 1

Text #17

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0173. Min Act: -0.0002

Data Index: 1380641 (Python Code)

Max Activating Token Index: 13

Text #18

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0171. Min Act: -0.0003

Data Index: 26171 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 0.0214. Min Range: -0.0214

Max Act: 0.0169. Min Act: -0.0003

Data Index: 264586 (C4 (Web Text))

Max Activating Token Index: 260