Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5171 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0308. Min Act: -0.0002

Data Index: 969717 (C4 (Web Text))

Max Activating Token Index: 726

Text #1

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0329. Min Act: -0.0002

Data Index: 626758 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0289. Min Act: -0.0002

Data Index: 381037 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0307. Min Act: -0.0002

Data Index: 443578 (C4 (Web Text))

Max Activating Token Index: 921

Text #4

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0302. Min Act: -0.0002

Data Index: 845893 (C4 (Web Text))

Max Activating Token Index: 1000

Text #5

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0285. Min Act: -0.0002

Data Index: 1049265 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0285. Min Act: -0.0002

Data Index: 247806 (C4 (Web Text))

Max Activating Token Index: 1003

Text #7

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0283. Min Act: -0.0002

Data Index: 861991 (C4 (Web Text))

Max Activating Token Index: 907

Text #8

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0277. Min Act: -0.0002

Data Index: 376795 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0261. Min Act: -0.0002

Data Index: 1113132 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0266. Min Act: -0.0002

Data Index: 1405973 (Python Code)

Max Activating Token Index: 319

Text #11

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0265. Min Act: -0.0002

Data Index: 135581 (C4 (Web Text))

Max Activating Token Index: 306

Text #12

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0260. Min Act: -0.0002

Data Index: 1431113 (Python Code)

Max Activating Token Index: 465

Text #13

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0265. Min Act: -0.0002

Data Index: 656283 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0273. Min Act: -0.0002

Data Index: 28169 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0303. Min Act: -0.0002

Data Index: 1598896 (Python Code)

Max Activating Token Index: 697

Text #16

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0268. Min Act: -0.0002

Data Index: 709347 (C4 (Web Text))

Max Activating Token Index: 960

Text #17

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0263. Min Act: -0.0002

Data Index: 1176421 (C4 (Web Text))

Max Activating Token Index: 964

Text #18

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0247. Min Act: -0.0002

Data Index: 642280 (C4 (Web Text))

Max Activating Token Index: 422

Text #19

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0257. Min Act: -0.0002

Data Index: 920603 (C4 (Web Text))

Max Activating Token Index: 725