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

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

Neuron 3466 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0383. Min Act: -0.0001

Data Index: 1016911 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0348. Min Act: -0.0001

Data Index: 637883 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0346. Min Act: -0.0000

Data Index: 883044 (C4 (Web Text))

Max Activating Token Index: 296

Text #3

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0336. Min Act: -0.0000

Data Index: 1330775 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0310. Min Act: -0.0001

Data Index: 182986 (C4 (Web Text))

Max Activating Token Index: 843

Text #5

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0295. Min Act: -0.0000

Data Index: 1035798 (C4 (Web Text))

Max Activating Token Index: 509

Text #6

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0286. Min Act: -0.0000

Data Index: 15645 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0295. Min Act: -0.0001

Data Index: 600497 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0294. Min Act: -0.0000

Data Index: 223579 (C4 (Web Text))

Max Activating Token Index: 407

Text #9

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0272. Min Act: -0.0001

Data Index: 1242357 (C4 (Web Text))

Max Activating Token Index: 142

Text #10

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0303. Min Act: -0.0001

Data Index: 1289171 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0277. Min Act: -0.0001

Data Index: 707538 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0291. Min Act: -0.0000

Data Index: 598058 (C4 (Web Text))

Max Activating Token Index: 95

Text #13

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0265. Min Act: -0.0001

Data Index: 763875 (C4 (Web Text))

Max Activating Token Index: 50

Text #14

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0279. Min Act: -0.0001

Data Index: 1145951 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0287. Min Act: -0.0000

Data Index: 1116636 (C4 (Web Text))

Max Activating Token Index: 440

Text #16

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0271. Min Act: -0.0001

Data Index: 1116381 (C4 (Web Text))

Max Activating Token Index: 744

Text #17

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0262. Min Act: -0.0001

Data Index: 706096 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0271. Min Act: -0.0001

Data Index: 530377 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0278. Min Act: -0.0000

Data Index: 1359266 (C4 (Web Text))

Max Activating Token Index: 98