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

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

Neuron 4332 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0394. Min Act: -0.0002

Data Index: 1431146 (Python Code)

Max Activating Token Index: 233

Text #1

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0345. Min Act: -0.0003

Data Index: 1448355 (Python Code)

Max Activating Token Index: 176

Text #2

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0223. Min Act: -0.0002

Data Index: 1484705 (Python Code)

Max Activating Token Index: 834

Text #3

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0203. Min Act: -0.0003

Data Index: 1423625 (Python Code)

Max Activating Token Index: 46

Text #4

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0193. Min Act: -0.0002

Data Index: 1567467 (Python Code)

Max Activating Token Index: 398

Text #5

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0193. Min Act: -0.0002

Data Index: 1624383 (Python Code)

Max Activating Token Index: 386

Text #6

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0184. Min Act: -0.0003

Data Index: 1415849 (Python Code)

Max Activating Token Index: 601

Text #7

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0179. Min Act: -0.0003

Data Index: 1463035 (Python Code)

Max Activating Token Index: 522

Text #8

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0183. Min Act: -0.0003

Data Index: 1377937 (Python Code)

Max Activating Token Index: 27

Text #9

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0181. Min Act: -0.0002

Data Index: 1460619 (Python Code)

Max Activating Token Index: 356

Text #10

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0175. Min Act: -0.0002

Data Index: 1487189 (Python Code)

Max Activating Token Index: 328

Text #11

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0187. Min Act: -0.0003

Data Index: 1587258 (Python Code)

Max Activating Token Index: 635

Text #12

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0176. Min Act: -0.0003

Data Index: 1526974 (Python Code)

Max Activating Token Index: 223

Text #13

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0158. Min Act: -0.0003

Data Index: 1511633 (Python Code)

Max Activating Token Index: 286

Text #14

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0171. Min Act: -0.0002

Data Index: 1651828 (Python Code)

Max Activating Token Index: 647

Text #15

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0158. Min Act: -0.0002

Data Index: 1363904 (Python Code)

Max Activating Token Index: 716

Text #16

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0166. Min Act: -0.0002

Data Index: 878792 (C4 (Web Text))

Max Activating Token Index: 197

Text #17

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0155. Min Act: -0.0002

Data Index: 1633397 (Python Code)

Max Activating Token Index: 90

Text #18

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0154. Min Act: -0.0003

Data Index: 1395880 (Python Code)

Max Activating Token Index: 352

Text #19

Max Range: 0.0394. Min Range: -0.0394

Max Act: 0.0170. Min Act: -0.0003

Data Index: 1616269 (Python Code)

Max Activating Token Index: 691