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

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

Neuron 903 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.1589. Min Act: -0.0000

Data Index: 1197802 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.3300. Min Act: -0.0000

Data Index: 582707 (C4 (Web Text))

Max Activating Token Index: 968

Text #2

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.2613. Min Act: -0.0000

Data Index: 943473 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.2395. Min Act: -0.0000

Data Index: 86120 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.2421. Min Act: -0.0000

Data Index: 407860 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.1969. Min Act: -0.0000

Data Index: 1314880 (C4 (Web Text))

Max Activating Token Index: 347

Text #6

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.1770. Min Act: -0.0000

Data Index: 57938 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.1606. Min Act: -0.0000

Data Index: 734393 (C4 (Web Text))

Max Activating Token Index: 612

Text #8

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.2376. Min Act: -0.0000

Data Index: 237116 (C4 (Web Text))

Max Activating Token Index: 79

Text #9

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.1409. Min Act: -0.0000

Data Index: 264228 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.1773. Min Act: -0.0000

Data Index: 254361 (C4 (Web Text))

Max Activating Token Index: 1003

Text #11

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.0624. Min Act: -0.0000

Data Index: 632600 (C4 (Web Text))

Max Activating Token Index: 766

Text #12

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.1320. Min Act: -0.0000

Data Index: 952023 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.0958. Min Act: -0.0000

Data Index: 717629 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.0883. Min Act: -0.0000

Data Index: 1297698 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.1490. Min Act: -0.0000

Data Index: 1103194 (C4 (Web Text))

Max Activating Token Index: 928

Text #16

Max Range: 1.3300. Min Range: -1.3300

Max Act: 0.8930. Min Act: -0.0000

Data Index: 373091 (C4 (Web Text))

Max Activating Token Index: 641

Text #17

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.0230. Min Act: -0.0000

Data Index: 502447 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.0222. Min Act: -0.0000

Data Index: 396179 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 1.3300. Min Range: -1.3300

Max Act: 1.1044. Min Act: -0.0000

Data Index: 1060373 (C4 (Web Text))

Max Activating Token Index: 26