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

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

Neuron 1665 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: 0.0284. Min Range: -0.0284

Max Act: 0.0284. Min Act: -0.0003

Data Index: 1624390 (Python Code)

Max Activating Token Index: 747

Text #1

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0230. Min Act: -0.0002

Data Index: 1294554 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0234. Min Act: -0.0002

Data Index: 1429107 (Python Code)

Max Activating Token Index: 580

Text #3

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0208. Min Act: -0.0002

Data Index: 1512830 (Python Code)

Max Activating Token Index: 431

Text #4

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0196. Min Act: -0.0003

Data Index: 1474691 (Python Code)

Max Activating Token Index: 171

Text #5

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0199. Min Act: -0.0002

Data Index: 414399 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0177. Min Act: -0.0003

Data Index: 1514776 (Python Code)

Max Activating Token Index: 362

Text #7

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0173. Min Act: -0.0003

Data Index: 676243 (C4 (Web Text))

Max Activating Token Index: 346

Text #8

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0172. Min Act: -0.0002

Data Index: 145293 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0171. Min Act: -0.0002

Data Index: 1004783 (C4 (Web Text))

Max Activating Token Index: 616

Text #10

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0179. Min Act: -0.0003

Data Index: 1441270 (Python Code)

Max Activating Token Index: 231

Text #11

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0165. Min Act: -0.0003

Data Index: 1367076 (Python Code)

Max Activating Token Index: 185

Text #12

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0167. Min Act: -0.0002

Data Index: 1134595 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0163. Min Act: -0.0002

Data Index: 299621 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0162. Min Act: -0.0002

Data Index: 602959 (C4 (Web Text))

Max Activating Token Index: 98

Text #15

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0164. Min Act: -0.0003

Data Index: 1566399 (Python Code)

Max Activating Token Index: 162

Text #16

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0164. Min Act: -0.0002

Data Index: 223826 (C4 (Web Text))

Max Activating Token Index: 603

Text #17

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0175. Min Act: -0.0003

Data Index: 187303 (C4 (Web Text))

Max Activating Token Index: 287

Text #18

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0163. Min Act: -0.0002

Data Index: 991361 (C4 (Web Text))

Max Activating Token Index: 801

Text #19

Max Range: 0.0284. Min Range: -0.0284

Max Act: 0.0151. Min Act: -0.0002

Data Index: 1343696 (C4 (Web Text))

Max Activating Token Index: 254