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

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

Neuron 1670 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8427. Min Range: -1.8427

Max Act: 1.8427. Min Act: -0.0000

Data Index: 804130 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 1.8427. Min Range: -1.8427

Max Act: 1.7868. Min Act: -0.0000

Data Index: 1299844 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 1.8427. Min Range: -1.8427

Max Act: 1.7786. Min Act: -0.0000

Data Index: 216086 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 1.8427. Min Range: -1.8427

Max Act: 1.2077. Min Act: -0.0000

Data Index: 831130 (C4 (Web Text))

Max Activating Token Index: 633

Text #4

Max Range: 1.8427. Min Range: -1.8427

Max Act: 1.1170. Min Act: -0.0000

Data Index: 688975 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 1.8427. Min Range: -1.8427

Max Act: 1.1401. Min Act: -0.0000

Data Index: 1267861 (C4 (Web Text))

Max Activating Token Index: 920

Text #6

Max Range: 1.8427. Min Range: -1.8427

Max Act: 1.0901. Min Act: -0.0000

Data Index: 894364 (C4 (Web Text))

Max Activating Token Index: 416

Text #7

Max Range: 1.8427. Min Range: -1.8427

Max Act: 1.0783. Min Act: -0.0000

Data Index: 896077 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 1.8427. Min Range: -1.8427

Max Act: 1.0743. Min Act: -0.0000

Data Index: 505379 (C4 (Web Text))

Max Activating Token Index: 699

Text #9

Max Range: 1.8427. Min Range: -1.8427

Max Act: 1.0376. Min Act: -0.0000

Data Index: 432670 (C4 (Web Text))

Max Activating Token Index: 605

Text #10

Max Range: 1.8427. Min Range: -1.8427

Max Act: 1.0945. Min Act: -0.0000

Data Index: 1231307 (C4 (Web Text))

Max Activating Token Index: 115

Text #11

Max Range: 1.8427. Min Range: -1.8427

Max Act: 0.9844. Min Act: -0.0000

Data Index: 1222420 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 1.8427. Min Range: -1.8427

Max Act: 0.9843. Min Act: -0.0000

Data Index: 147023 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 1.8427. Min Range: -1.8427

Max Act: 0.9745. Min Act: -0.0000

Data Index: 792061 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 1.8427. Min Range: -1.8427

Max Act: 0.9172. Min Act: -0.0000

Data Index: 1134970 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 1.8427. Min Range: -1.8427

Max Act: 0.9260. Min Act: -0.0000

Data Index: 1272986 (C4 (Web Text))

Max Activating Token Index: 218

Text #16

Max Range: 1.8427. Min Range: -1.8427

Max Act: 0.9131. Min Act: -0.0000

Data Index: 1247352 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 1.8427. Min Range: -1.8427

Max Act: 0.9333. Min Act: -0.0000

Data Index: 19568 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 1.8427. Min Range: -1.8427

Max Act: 0.9019. Min Act: -0.0000

Data Index: 605835 (C4 (Web Text))

Max Activating Token Index: 575

Text #19

Max Range: 1.8427. Min Range: -1.8427

Max Act: 0.9289. Min Act: -0.0000

Data Index: 628077 (C4 (Web Text))

Max Activating Token Index: 555