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

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

Neuron 4746 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.8606. Min Act: -0.0000

Data Index: 113729 (C4 (Web Text))

Max Activating Token Index: 111

Text #1

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.8439. Min Act: -0.0000

Data Index: 1298009 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.8572. Min Act: -0.0000

Data Index: 189561 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.6615. Min Act: -0.0000

Data Index: 382607 (C4 (Web Text))

Max Activating Token Index: 791

Text #4

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.7037. Min Act: -0.0000

Data Index: 1154158 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.7130. Min Act: -0.0000

Data Index: 1341274 (C4 (Web Text))

Max Activating Token Index: 351

Text #6

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.6739. Min Act: -0.0000

Data Index: 788153 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.6428. Min Act: -0.0000

Data Index: 388194 (C4 (Web Text))

Max Activating Token Index: 307

Text #8

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.6972. Min Act: -0.0000

Data Index: 509707 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.6376. Min Act: -0.0000

Data Index: 1359026 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.5958. Min Act: -0.0000

Data Index: 1170114 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.6564. Min Act: 0.0000

Data Index: 21305 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.6038. Min Act: -0.0000

Data Index: 50708 (C4 (Web Text))

Max Activating Token Index: 238

Text #13

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.6434. Min Act: -0.0000

Data Index: 746751 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.6205. Min Act: -0.0000

Data Index: 1343263 (C4 (Web Text))

Max Activating Token Index: 307

Text #15

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.6165. Min Act: -0.0000

Data Index: 1307597 (C4 (Web Text))

Max Activating Token Index: 428

Text #16

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.6049. Min Act: -0.0000

Data Index: 1070148 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.6232. Min Act: -0.0000

Data Index: 823673 (C4 (Web Text))

Max Activating Token Index: 321

Text #18

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.6331. Min Act: -0.0000

Data Index: 507212 (C4 (Web Text))

Max Activating Token Index: 961

Text #19

Max Range: 0.8606. Min Range: -0.8606

Max Act: 0.5663. Min Act: -0.0000

Data Index: 1028345 (C4 (Web Text))

Max Activating Token Index: 868