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

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

Neuron 1363 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0300. Min Range: -1.0300

Max Act: 1.0300. Min Act: -0.0000

Data Index: 725364 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.8319. Min Act: -0.0000

Data Index: 85036 (C4 (Web Text))

Max Activating Token Index: 682

Text #2

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.6818. Min Act: -0.0000

Data Index: 818505 (C4 (Web Text))

Max Activating Token Index: 1007

Text #3

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.7898. Min Act: -0.0000

Data Index: 312876 (C4 (Web Text))

Max Activating Token Index: 133

Text #4

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.7217. Min Act: -0.0000

Data Index: 1164966 (C4 (Web Text))

Max Activating Token Index: 527

Text #5

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.6664. Min Act: -0.0000

Data Index: 28999 (C4 (Web Text))

Max Activating Token Index: 966

Text #6

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.6620. Min Act: -0.0000

Data Index: 1124646 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.6182. Min Act: -0.0000

Data Index: 855753 (C4 (Web Text))

Max Activating Token Index: 477

Text #8

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.6236. Min Act: -0.0000

Data Index: 525003 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.6390. Min Act: -0.0000

Data Index: 413833 (C4 (Web Text))

Max Activating Token Index: 294

Text #10

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.5847. Min Act: -0.0000

Data Index: 834628 (C4 (Web Text))

Max Activating Token Index: 372

Text #11

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.6014. Min Act: -0.0000

Data Index: 556979 (C4 (Web Text))

Max Activating Token Index: 712

Text #12

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.5770. Min Act: -0.0000

Data Index: 995483 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.5847. Min Act: -0.0000

Data Index: 634366 (C4 (Web Text))

Max Activating Token Index: 558

Text #14

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.5287. Min Act: -0.0000

Data Index: 330873 (C4 (Web Text))

Max Activating Token Index: 179

Text #15

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.5657. Min Act: -0.0000

Data Index: 1299352 (C4 (Web Text))

Max Activating Token Index: 922

Text #16

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.5081. Min Act: -0.0000

Data Index: 351310 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.5240. Min Act: -0.0000

Data Index: 221181 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.5032. Min Act: -0.0000

Data Index: 85962 (C4 (Web Text))

Max Activating Token Index: 418

Text #19

Max Range: 1.0300. Min Range: -1.0300

Max Act: 0.5183. Min Act: -0.0000

Data Index: 1244677 (C4 (Web Text))

Max Activating Token Index: 514