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

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

Neuron 754 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2110. Min Range: -1.2110

Max Act: 1.2110. Min Act: -0.0001

Data Index: 943775 (C4 (Web Text))

Max Activating Token Index: 312

Text #1

Max Range: 1.2110. Min Range: -1.2110

Max Act: 1.0174. Min Act: -0.0001

Data Index: 212514 (C4 (Web Text))

Max Activating Token Index: 101

Text #2

Max Range: 1.2110. Min Range: -1.2110

Max Act: 1.0959. Min Act: -0.0001

Data Index: 1211363 (C4 (Web Text))

Max Activating Token Index: 222

Text #3

Max Range: 1.2110. Min Range: -1.2110

Max Act: 1.0744. Min Act: -0.0001

Data Index: 1346062 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 1.2110. Min Range: -1.2110

Max Act: 0.9834. Min Act: -0.0001

Data Index: 733443 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 1.2110. Min Range: -1.2110

Max Act: 0.9523. Min Act: -0.0001

Data Index: 1127445 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 1.2110. Min Range: -1.2110

Max Act: 0.9346. Min Act: -0.0001

Data Index: 57006 (C4 (Web Text))

Max Activating Token Index: 837

Text #7

Max Range: 1.2110. Min Range: -1.2110

Max Act: 0.8833. Min Act: -0.0001

Data Index: 1357263 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 1.2110. Min Range: -1.2110

Max Act: 0.9385. Min Act: -0.0001

Data Index: 264452 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 1.2110. Min Range: -1.2110

Max Act: 0.9106. Min Act: -0.0001

Data Index: 973559 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 1.2110. Min Range: -1.2110

Max Act: 0.9024. Min Act: -0.0001

Data Index: 671891 (C4 (Web Text))

Max Activating Token Index: 324

Text #11

Max Range: 1.2110. Min Range: -1.2110

Max Act: 0.9222. Min Act: -0.0001

Data Index: 1164133 (C4 (Web Text))

Max Activating Token Index: 244

Text #12

Max Range: 1.2110. Min Range: -1.2110

Max Act: 0.8760. Min Act: -0.0001

Data Index: 616151 (C4 (Web Text))

Max Activating Token Index: 275

Text #13

Max Range: 1.2110. Min Range: -1.2110

Max Act: 0.8445. Min Act: -0.0001

Data Index: 1154675 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 1.2110. Min Range: -1.2110

Max Act: 0.9267. Min Act: -0.0001

Data Index: 977318 (C4 (Web Text))

Max Activating Token Index: 650

Text #15

Max Range: 1.2110. Min Range: -1.2110

Max Act: 0.8940. Min Act: -0.0001

Data Index: 754988 (C4 (Web Text))

Max Activating Token Index: 494

Text #16

Max Range: 1.2110. Min Range: -1.2110

Max Act: 0.8982. Min Act: -0.0001

Data Index: 704783 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 1.2110. Min Range: -1.2110

Max Act: 0.8560. Min Act: -0.0001

Data Index: 1068506 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 1.2110. Min Range: -1.2110

Max Act: 0.8739. Min Act: -0.0001

Data Index: 296086 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 1.2110. Min Range: -1.2110

Max Act: 0.8463. Min Act: -0.0001

Data Index: 135149 (C4 (Web Text))

Max Activating Token Index: 500