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

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

Neuron 1640 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7018. Min Range: -2.7018

Max Act: 2.7014. Min Act: -0.0000

Data Index: 1196783 (C4 (Web Text))

Max Activating Token Index: 413

Text #1

Max Range: 2.7018. Min Range: -2.7018

Max Act: 2.5941. Min Act: -0.0000

Data Index: 1020145 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 2.7018. Min Range: -2.7018

Max Act: 2.6894. Min Act: -0.0000

Data Index: 649960 (C4 (Web Text))

Max Activating Token Index: 609

Text #3

Max Range: 2.7018. Min Range: -2.7018

Max Act: 2.5401. Min Act: -0.0000

Data Index: 236507 (C4 (Web Text))

Max Activating Token Index: 59

Text #4

Max Range: 2.7018. Min Range: -2.7018

Max Act: 2.3511. Min Act: -0.0000

Data Index: 930964 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 2.7018. Min Range: -2.7018

Max Act: 2.3385. Min Act: -0.0000

Data Index: 1358994 (C4 (Web Text))

Max Activating Token Index: 595

Text #6

Max Range: 2.7018. Min Range: -2.7018

Max Act: 2.5770. Min Act: -0.0000

Data Index: 816320 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 2.7018. Min Range: -2.7018

Max Act: 2.4225. Min Act: -0.0000

Data Index: 1265747 (C4 (Web Text))

Max Activating Token Index: 215

Text #8

Max Range: 2.7018. Min Range: -2.7018

Max Act: 2.7000. Min Act: -0.0000

Data Index: 525759 (C4 (Web Text))

Max Activating Token Index: 838

Text #9

Max Range: 2.7018. Min Range: -2.7018

Max Act: 2.5180. Min Act: -0.0000

Data Index: 233745 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 2.7018. Min Range: -2.7018

Max Act: 2.0559. Min Act: -0.0000

Data Index: 970857 (C4 (Web Text))

Max Activating Token Index: 247

Text #11

Max Range: 2.7018. Min Range: -2.7018

Max Act: 2.1557. Min Act: -0.0000

Data Index: 1039249 (C4 (Web Text))

Max Activating Token Index: 237

Text #12

Max Range: 2.7018. Min Range: -2.7018

Max Act: 2.3676. Min Act: -0.0000

Data Index: 22701 (C4 (Web Text))

Max Activating Token Index: 843

Text #13

Max Range: 2.7018. Min Range: -2.7018

Max Act: 2.2382. Min Act: -0.0000

Data Index: 1029148 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 2.7018. Min Range: -2.7018

Max Act: 2.2160. Min Act: -0.0000

Data Index: 284503 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 2.7018. Min Range: -2.7018

Max Act: 2.4779. Min Act: -0.0000

Data Index: 1091369 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 2.7018. Min Range: -2.7018

Max Act: 2.7018. Min Act: -0.0000

Data Index: 415829 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 2.7018. Min Range: -2.7018

Max Act: 2.3345. Min Act: -0.0000

Data Index: 907880 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 2.7018. Min Range: -2.7018

Max Act: 2.4378. Min Act: -0.0000

Data Index: 610865 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 2.7018. Min Range: -2.7018

Max Act: 2.3185. Min Act: -0.0000

Data Index: 740594 (C4 (Web Text))

Max Activating Token Index: 347