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

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

Neuron 1898 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: 0.0233. Min Range: -0.0233

Max Act: 0.0233. Min Act: -0.0002

Data Index: 437922 (C4 (Web Text))

Max Activating Token Index: 858

Text #1

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0205. Min Act: -0.0002

Data Index: 1647447 (Python Code)

Max Activating Token Index: 709

Text #2

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0186. Min Act: -0.0002

Data Index: 1654134 (Python Code)

Max Activating Token Index: 223

Text #3

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0181. Min Act: -0.0002

Data Index: 377960 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0183. Min Act: -0.0002

Data Index: 1365470 (Python Code)

Max Activating Token Index: 992

Text #5

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0185. Min Act: -0.0002

Data Index: 1186926 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0187. Min Act: -0.0002

Data Index: 972927 (C4 (Web Text))

Max Activating Token Index: 1012

Text #7

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0184. Min Act: -0.0002

Data Index: 31485 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0180. Min Act: -0.0002

Data Index: 1621683 (Python Code)

Max Activating Token Index: 454

Text #9

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0178. Min Act: -0.0002

Data Index: 1451554 (Python Code)

Max Activating Token Index: 173

Text #10

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0178. Min Act: -0.0002

Data Index: 1614554 (Python Code)

Max Activating Token Index: 937

Text #11

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0179. Min Act: -0.0002

Data Index: 724019 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0168. Min Act: -0.0002

Data Index: 1007189 (C4 (Web Text))

Max Activating Token Index: 156

Text #13

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0179. Min Act: -0.0002

Data Index: 989547 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0164. Min Act: -0.0002

Data Index: 1601859 (Python Code)

Max Activating Token Index: 854

Text #15

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0173. Min Act: -0.0002

Data Index: 590521 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0164. Min Act: -0.0002

Data Index: 1436633 (Python Code)

Max Activating Token Index: 14

Text #17

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0162. Min Act: -0.0002

Data Index: 933411 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0175. Min Act: -0.0002

Data Index: 709773 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 0.0233. Min Range: -0.0233

Max Act: 0.0162. Min Act: -0.0002

Data Index: 1458729 (Python Code)

Max Activating Token Index: 616