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

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

Neuron 5426 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.1512. Min Act: -0.0001

Data Index: 344137 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.1513. Min Act: -0.0001

Data Index: 810681 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.1542. Min Act: -0.0002

Data Index: 130792 (C4 (Web Text))

Max Activating Token Index: 615

Text #3

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.1243. Min Act: -0.0001

Data Index: 1441441 (Python Code)

Max Activating Token Index: 283

Text #4

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.1401. Min Act: -0.0001

Data Index: 1090677 (C4 (Web Text))

Max Activating Token Index: 564

Text #5

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.1199. Min Act: -0.0001

Data Index: 941180 (C4 (Web Text))

Max Activating Token Index: 328

Text #6

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.0977. Min Act: -0.0001

Data Index: 351570 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.1633. Min Act: -0.0001

Data Index: 674193 (C4 (Web Text))

Max Activating Token Index: 812

Text #8

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.1323. Min Act: -0.0001

Data Index: 61489 (C4 (Web Text))

Max Activating Token Index: 470

Text #9

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.1270. Min Act: -0.0001

Data Index: 751725 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.1307. Min Act: -0.0001

Data Index: 453430 (C4 (Web Text))

Max Activating Token Index: 159

Text #11

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.1313. Min Act: -0.0001

Data Index: 1091150 (C4 (Web Text))

Max Activating Token Index: 486

Text #12

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.1264. Min Act: -0.0001

Data Index: 980880 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.1215. Min Act: -0.0001

Data Index: 1105551 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.1238. Min Act: -0.0001

Data Index: 80091 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.1089. Min Act: -0.0001

Data Index: 783477 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.1216. Min Act: -0.0001

Data Index: 988403 (C4 (Web Text))

Max Activating Token Index: 37

Text #17

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.1125. Min Act: -0.0001

Data Index: 600841 (C4 (Web Text))

Max Activating Token Index: 900

Text #18

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.1340. Min Act: -0.0001

Data Index: 1210376 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 0.1633. Min Range: -0.1633

Max Act: 0.1268. Min Act: -0.0001

Data Index: 705033 (C4 (Web Text))

Max Activating Token Index: 789