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

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

Neuron 1634 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2850. Min Act: -0.0000

Data Index: 10336 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2320. Min Act: -0.0000

Data Index: 1314640 (C4 (Web Text))

Max Activating Token Index: 97

Text #2

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2246. Min Act: -0.0000

Data Index: 557020 (C4 (Web Text))

Max Activating Token Index: 362

Text #3

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2156. Min Act: -0.0000

Data Index: 967111 (C4 (Web Text))

Max Activating Token Index: 97

Text #4

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2080. Min Act: -0.0000

Data Index: 275798 (C4 (Web Text))

Max Activating Token Index: 1003

Text #5

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2043. Min Act: -0.0000

Data Index: 1193008 (C4 (Web Text))

Max Activating Token Index: 446

Text #6

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2099. Min Act: -0.0000

Data Index: 1289899 (C4 (Web Text))

Max Activating Token Index: 1002

Text #7

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2018. Min Act: -0.0000

Data Index: 1264406 (C4 (Web Text))

Max Activating Token Index: 411

Text #8

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.1986. Min Act: -0.0000

Data Index: 1300333 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.1963. Min Act: -0.0000

Data Index: 1220437 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2014. Min Act: -0.0000

Data Index: 284819 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.2011. Min Act: -0.0000

Data Index: 379723 (C4 (Web Text))

Max Activating Token Index: 655

Text #12

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.1959. Min Act: 0.0000

Data Index: 774672 (C4 (Web Text))

Max Activating Token Index: 103

Text #13

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.1795. Min Act: -0.0000

Data Index: 658100 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.1812. Min Act: -0.0000

Data Index: 1244697 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.1758. Min Act: -0.0000

Data Index: 349675 (C4 (Web Text))

Max Activating Token Index: 683

Text #16

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.1782. Min Act: 0.0000

Data Index: 666511 (C4 (Web Text))

Max Activating Token Index: 257

Text #17

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.1854. Min Act: -0.0000

Data Index: 507785 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.1743. Min Act: -0.0000

Data Index: 255968 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 0.2850. Min Range: -0.2850

Max Act: 0.1766. Min Act: -0.0000

Data Index: 542810 (C4 (Web Text))

Max Activating Token Index: 341