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

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

Neuron 5089 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1686. Min Act: -0.0001

Data Index: 1317955 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1646. Min Act: -0.0002

Data Index: 957775 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1612. Min Act: -0.0001

Data Index: 1245801 (C4 (Web Text))

Max Activating Token Index: 250

Text #3

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1534. Min Act: 0.0001

Data Index: 454369 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1529. Min Act: 0.0002

Data Index: 490891 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1507. Min Act: -0.0002

Data Index: 964863 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1505. Min Act: 0.0002

Data Index: 660615 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1497. Min Act: -0.0002

Data Index: 847660 (C4 (Web Text))

Max Activating Token Index: 53

Text #8

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1493. Min Act: -0.0001

Data Index: 1014264 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1482. Min Act: -0.0001

Data Index: 119578 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1406. Min Act: -0.0001

Data Index: 1199480 (C4 (Web Text))

Max Activating Token Index: 85

Text #11

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1442. Min Act: -0.0001

Data Index: 354896 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1439. Min Act: -0.0001

Data Index: 1071926 (C4 (Web Text))

Max Activating Token Index: 32

Text #13

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1425. Min Act: -0.0001

Data Index: 286791 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1421. Min Act: -0.0001

Data Index: 234137 (C4 (Web Text))

Max Activating Token Index: 581

Text #15

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1415. Min Act: -0.0001

Data Index: 1032324 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1400. Min Act: -0.0002

Data Index: 597859 (C4 (Web Text))

Max Activating Token Index: 182

Text #17

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1386. Min Act: -0.0001

Data Index: 19222 (C4 (Web Text))

Max Activating Token Index: 102

Text #18

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1385. Min Act: -0.0002

Data Index: 1330628 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1430. Min Act: -0.0001

Data Index: 1244395 (C4 (Web Text))

Max Activating Token Index: 11