Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1162 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1719. Min Act: -0.0002

Data Index: 1471365 (Python Code)

Max Activating Token Index: 77

Text #1

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1575. Min Act: -0.0002

Data Index: 1583559 (Python Code)

Max Activating Token Index: 77

Text #2

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1339. Min Act: -0.0002

Data Index: 1561328 (Python Code)

Max Activating Token Index: 956

Text #3

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1359. Min Act: -0.0002

Data Index: 1487816 (Python Code)

Max Activating Token Index: 214

Text #4

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1380. Min Act: -0.0002

Data Index: 3625 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1257. Min Act: -0.0002

Data Index: 1643976 (Python Code)

Max Activating Token Index: 79

Text #6

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1294. Min Act: -0.0002

Data Index: 1515992 (Python Code)

Max Activating Token Index: 66

Text #7

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1332. Min Act: -0.0002

Data Index: 1483535 (Python Code)

Max Activating Token Index: 419

Text #8

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1264. Min Act: -0.0002

Data Index: 1429458 (Python Code)

Max Activating Token Index: 190

Text #9

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1269. Min Act: -0.0002

Data Index: 1376396 (Python Code)

Max Activating Token Index: 943

Text #10

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1219. Min Act: -0.0002

Data Index: 1468342 (Python Code)

Max Activating Token Index: 48

Text #11

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1169. Min Act: -0.0002

Data Index: 255979 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1180. Min Act: -0.0002

Data Index: 1582557 (Python Code)

Max Activating Token Index: 967

Text #13

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1242. Min Act: -0.0002

Data Index: 1504075 (Python Code)

Max Activating Token Index: 508

Text #14

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1167. Min Act: -0.0002

Data Index: 1408942 (Python Code)

Max Activating Token Index: 586

Text #15

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1183. Min Act: -0.0002

Data Index: 1208915 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1116. Min Act: -0.0002

Data Index: 1322917 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1186. Min Act: -0.0002

Data Index: 1536880 (Python Code)

Max Activating Token Index: 99

Text #18

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1177. Min Act: -0.0002

Data Index: 978279 (C4 (Web Text))

Max Activating Token Index: 859

Text #19

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1159. Min Act: -0.0002

Data Index: 920858 (C4 (Web Text))

Max Activating Token Index: 742