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

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

Neuron 3303 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1900. Min Act: -0.0001

Data Index: 1496769 (Python Code)

Max Activating Token Index: 549

Text #1

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1812. Min Act: -0.0001

Data Index: 1412905 (Python Code)

Max Activating Token Index: 889

Text #2

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1820. Min Act: -0.0001

Data Index: 1472928 (Python Code)

Max Activating Token Index: 155

Text #3

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1715. Min Act: -0.0001

Data Index: 1524711 (Python Code)

Max Activating Token Index: 404

Text #4

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1657. Min Act: -0.0001

Data Index: 1529763 (Python Code)

Max Activating Token Index: 62

Text #5

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1584. Min Act: -0.0001

Data Index: 1582277 (Python Code)

Max Activating Token Index: 395

Text #6

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1681. Min Act: -0.0001

Data Index: 1533769 (Python Code)

Max Activating Token Index: 165

Text #7

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1566. Min Act: -0.0001

Data Index: 1422937 (Python Code)

Max Activating Token Index: 95

Text #8

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1528. Min Act: -0.0001

Data Index: 1613634 (Python Code)

Max Activating Token Index: 699

Text #9

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1560. Min Act: -0.0001

Data Index: 1617487 (Python Code)

Max Activating Token Index: 890

Text #10

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1534. Min Act: -0.0001

Data Index: 1472038 (Python Code)

Max Activating Token Index: 77

Text #11

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1472. Min Act: -0.0001

Data Index: 1539224 (Python Code)

Max Activating Token Index: 537

Text #12

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1419. Min Act: -0.0001

Data Index: 1645930 (Python Code)

Max Activating Token Index: 133

Text #13

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1436. Min Act: -0.0001

Data Index: 1567809 (Python Code)

Max Activating Token Index: 35

Text #14

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1423. Min Act: -0.0001

Data Index: 1550590 (Python Code)

Max Activating Token Index: 28

Text #15

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1362. Min Act: -0.0001

Data Index: 1578719 (Python Code)

Max Activating Token Index: 171

Text #16

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1368. Min Act: -0.0001

Data Index: 1627444 (Python Code)

Max Activating Token Index: 793

Text #17

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1393. Min Act: -0.0001

Data Index: 1408153 (Python Code)

Max Activating Token Index: 202

Text #18

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1396. Min Act: -0.0001

Data Index: 1433175 (Python Code)

Max Activating Token Index: 602

Text #19

Max Range: 0.1900. Min Range: -0.1900

Max Act: 0.1390. Min Act: -0.0001

Data Index: 1574651 (Python Code)

Max Activating Token Index: 556