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

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

Neuron 2930 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: 0.1843. Min Range: -0.1843

Max Act: 0.1771. Min Act: -0.0000

Data Index: 1231684 (C4 (Web Text))

Max Activating Token Index: 100

Text #1

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1843. Min Act: -0.0000

Data Index: 1213012 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1629. Min Act: -0.0000

Data Index: 401614 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1630. Min Act: -0.0000

Data Index: 1025641 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1515. Min Act: -0.0000

Data Index: 1241194 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1504. Min Act: -0.0000

Data Index: 1218571 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1453. Min Act: -0.0000

Data Index: 636021 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1494. Min Act: -0.0000

Data Index: 714275 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1427. Min Act: -0.0000

Data Index: 220003 (C4 (Web Text))

Max Activating Token Index: 86

Text #9

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1478. Min Act: -0.0000

Data Index: 50106 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1384. Min Act: -0.0000

Data Index: 1220178 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1376. Min Act: -0.0000

Data Index: 1145973 (C4 (Web Text))

Max Activating Token Index: 45

Text #12

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1465. Min Act: -0.0000

Data Index: 1503232 (Python Code)

Max Activating Token Index: 505

Text #13

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1415. Min Act: -0.0000

Data Index: 720194 (C4 (Web Text))

Max Activating Token Index: 194

Text #14

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1454. Min Act: -0.0000

Data Index: 881014 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1302. Min Act: -0.0000

Data Index: 726116 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1349. Min Act: -0.0000

Data Index: 1290690 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1342. Min Act: -0.0000

Data Index: 790784 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1337. Min Act: -0.0000

Data Index: 1143452 (C4 (Web Text))

Max Activating Token Index: 203

Text #19

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1251. Min Act: -0.0000

Data Index: 1609558 (Python Code)

Max Activating Token Index: 764