Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 994 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1885. Min Act: -0.0000

Data Index: 528050 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1743. Min Act: -0.0000

Data Index: 930443 (C4 (Web Text))

Max Activating Token Index: 576

Text #2

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1526. Min Act: -0.0001

Data Index: 1214102 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1482. Min Act: -0.0001

Data Index: 1035874 (C4 (Web Text))

Max Activating Token Index: 627

Text #4

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1460. Min Act: -0.0001

Data Index: 1192504 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1448. Min Act: -0.0000

Data Index: 386940 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1447. Min Act: -0.0000

Data Index: 454345 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1532. Min Act: -0.0001

Data Index: 1005093 (C4 (Web Text))

Max Activating Token Index: 440

Text #8

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1423. Min Act: -0.0001

Data Index: 1223941 (C4 (Web Text))

Max Activating Token Index: 904

Text #9

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1501. Min Act: -0.0000

Data Index: 724390 (C4 (Web Text))

Max Activating Token Index: 767

Text #10

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1379. Min Act: -0.0001

Data Index: 254208 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1418. Min Act: -0.0001

Data Index: 826242 (C4 (Web Text))

Max Activating Token Index: 40

Text #12

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1408. Min Act: -0.0000

Data Index: 118363 (C4 (Web Text))

Max Activating Token Index: 915

Text #13

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1392. Min Act: -0.0000

Data Index: 890120 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1455. Min Act: -0.0000

Data Index: 1025223 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1333. Min Act: -0.0000

Data Index: 46171 (C4 (Web Text))

Max Activating Token Index: 1021

Text #16

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1363. Min Act: -0.0001

Data Index: 1114343 (C4 (Web Text))

Max Activating Token Index: 174

Text #17

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1356. Min Act: -0.0001

Data Index: 365272 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1355. Min Act: -0.0000

Data Index: 740342 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 0.1885. Min Range: -0.1885

Max Act: 0.1404. Min Act: -0.0000

Data Index: 705068 (C4 (Web Text))

Max Activating Token Index: 102