Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2407 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.2257. Min Act: -0.0001

Data Index: 1206438 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1927. Min Act: -0.0001

Data Index: 1241716 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.2015. Min Act: -0.0001

Data Index: 643332 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1971. Min Act: -0.0001

Data Index: 751154 (C4 (Web Text))

Max Activating Token Index: 196

Text #4

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1891. Min Act: -0.0001

Data Index: 214762 (C4 (Web Text))

Max Activating Token Index: 868

Text #5

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1915. Min Act: -0.0001

Data Index: 941212 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1662. Min Act: -0.0001

Data Index: 284074 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1824. Min Act: -0.0001

Data Index: 647734 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1770. Min Act: -0.0001

Data Index: 360818 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1794. Min Act: -0.0001

Data Index: 942061 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1717. Min Act: -0.0001

Data Index: 705348 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1755. Min Act: -0.0001

Data Index: 297375 (C4 (Web Text))

Max Activating Token Index: 410

Text #12

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1730. Min Act: -0.0001

Data Index: 1118846 (C4 (Web Text))

Max Activating Token Index: 113

Text #13

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1753. Min Act: -0.0001

Data Index: 476561 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1806. Min Act: -0.0001

Data Index: 566810 (C4 (Web Text))

Max Activating Token Index: 628

Text #15

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1698. Min Act: -0.0001

Data Index: 819638 (C4 (Web Text))

Max Activating Token Index: 331

Text #16

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1628. Min Act: -0.0001

Data Index: 972182 (C4 (Web Text))

Max Activating Token Index: 75

Text #17

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1572. Min Act: -0.0001

Data Index: 487498 (C4 (Web Text))

Max Activating Token Index: 169

Text #18

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1673. Min Act: -0.0001

Data Index: 16445 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 0.2257. Min Range: -0.2257

Max Act: 0.1723. Min Act: -0.0001

Data Index: 716548 (C4 (Web Text))

Max Activating Token Index: 502