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

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

Neuron 1165 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.3142. Min Act: -0.0000

Data Index: 122973 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2845. Min Act: -0.0000

Data Index: 264601 (C4 (Web Text))

Max Activating Token Index: 1020

Text #2

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2633. Min Act: -0.0000

Data Index: 834631 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2477. Min Act: -0.0000

Data Index: 1174355 (C4 (Web Text))

Max Activating Token Index: 672

Text #4

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2548. Min Act: 0.0000

Data Index: 642940 (C4 (Web Text))

Max Activating Token Index: 533

Text #5

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2491. Min Act: -0.0000

Data Index: 324812 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2500. Min Act: -0.0000

Data Index: 1348066 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2461. Min Act: -0.0000

Data Index: 122797 (C4 (Web Text))

Max Activating Token Index: 193

Text #8

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2433. Min Act: -0.0000

Data Index: 1189572 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2251. Min Act: -0.0000

Data Index: 1321014 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2286. Min Act: -0.0000

Data Index: 180656 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2289. Min Act: 0.0000

Data Index: 489861 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2233. Min Act: -0.0000

Data Index: 268487 (C4 (Web Text))

Max Activating Token Index: 835

Text #13

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2151. Min Act: -0.0000

Data Index: 235300 (C4 (Web Text))

Max Activating Token Index: 441

Text #14

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2286. Min Act: -0.0000

Data Index: 470342 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2135. Min Act: -0.0000

Data Index: 311096 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2180. Min Act: -0.0000

Data Index: 127958 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2016. Min Act: -0.0000

Data Index: 277285 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.1991. Min Act: 0.0000

Data Index: 331069 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 0.3142. Min Range: -0.3142

Max Act: 0.2016. Min Act: -0.0000

Data Index: 920032 (C4 (Web Text))

Max Activating Token Index: 322