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

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

Neuron 4317 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.2015. Min Act: -0.0002

Data Index: 1108285 (C4 (Web Text))

Max Activating Token Index: 57

Text #1

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1905. Min Act: -0.0002

Data Index: 812819 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.2031. Min Act: -0.0002

Data Index: 1074597 (C4 (Web Text))

Max Activating Token Index: 398

Text #3

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1623. Min Act: -0.0002

Data Index: 759166 (C4 (Web Text))

Max Activating Token Index: 106

Text #4

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1536. Min Act: -0.0002

Data Index: 339194 (C4 (Web Text))

Max Activating Token Index: 183

Text #5

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1440. Min Act: -0.0002

Data Index: 1155462 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1392. Min Act: -0.0002

Data Index: 1292169 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1405. Min Act: -0.0002

Data Index: 594516 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1416. Min Act: -0.0002

Data Index: 1343130 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1395. Min Act: -0.0002

Data Index: 373564 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1386. Min Act: -0.0002

Data Index: 152024 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1376. Min Act: -0.0002

Data Index: 674348 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1404. Min Act: -0.0002

Data Index: 1062167 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1187. Min Act: -0.0002

Data Index: 108795 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1333. Min Act: -0.0002

Data Index: 281631 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1317. Min Act: -0.0002

Data Index: 303479 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1301. Min Act: -0.0002

Data Index: 799792 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1305. Min Act: -0.0002

Data Index: 1160437 (C4 (Web Text))

Max Activating Token Index: 297

Text #18

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1292. Min Act: -0.0002

Data Index: 186786 (C4 (Web Text))

Max Activating Token Index: 223

Text #19

Max Range: 0.2031. Min Range: -0.2031

Max Act: 0.1286. Min Act: -0.0002

Data Index: 785168 (C4 (Web Text))

Max Activating Token Index: 85