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

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

Neuron 3934 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2037. Min Range: -0.2037

Max Act: 0.2037. Min Act: -0.0001

Data Index: 352248 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 0.2037. Min Range: -0.2037

Max Act: 0.1917. Min Act: -0.0001

Data Index: 1303662 (C4 (Web Text))

Max Activating Token Index: 747

Text #2

Max Range: 0.2037. Min Range: -0.2037

Max Act: 0.1914. Min Act: -0.0001

Data Index: 1283753 (C4 (Web Text))

Max Activating Token Index: 775

Text #3

Max Range: 0.2037. Min Range: -0.2037

Max Act: 0.1885. Min Act: -0.0001

Data Index: 405148 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 0.2037. Min Range: -0.2037

Max Act: 0.1782. Min Act: -0.0001

Data Index: 1095750 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 0.2037. Min Range: -0.2037

Max Act: 0.1753. Min Act: -0.0001

Data Index: 1433186 (Python Code)

Max Activating Token Index: 27

Text #6

Max Range: 0.2037. Min Range: -0.2037

Max Act: 0.1817. Min Act: -0.0001

Data Index: 1372699 (Python Code)

Max Activating Token Index: 19

Text #7

Max Range: 0.2037. Min Range: -0.2037

Max Act: 0.1672. Min Act: -0.0001

Data Index: 135237 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 0.2037. Min Range: -0.2037

Max Act: 0.1667. Min Act: -0.0001

Data Index: 886484 (C4 (Web Text))

Max Activating Token Index: 471

Text #9

Max Range: 0.2037. Min Range: -0.2037

Max Act: 0.1620. Min Act: -0.0001

Data Index: 135942 (C4 (Web Text))

Max Activating Token Index: 393

Text #10

Max Range: 0.2037. Min Range: -0.2037

Max Act: 0.1549. Min Act: -0.0001

Data Index: 127411 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 0.2037. Min Range: -0.2037

Max Act: 0.1577. Min Act: -0.0001

Data Index: 1411250 (Python Code)

Max Activating Token Index: 275

Text #12

Max Range: 0.2037. Min Range: -0.2037

Max Act: 0.1578. Min Act: -0.0001

Data Index: 73907 (C4 (Web Text))

Max Activating Token Index: 890

Text #13

Max Range: 0.2037. Min Range: -0.2037

Max Act: 0.1631. Min Act: -0.0001

Data Index: 1565305 (Python Code)

Max Activating Token Index: 19

Text #14

Max Range: 0.2037. Min Range: -0.2037

Max Act: 0.1816. Min Act: -0.0001

Data Index: 359077 (C4 (Web Text))

Max Activating Token Index: 60

Text #15

Max Range: 0.2037. Min Range: -0.2037

Max Act: 0.1516. Min Act: -0.0001

Data Index: 834565 (C4 (Web Text))

Max Activating Token Index: 523

Text #16

Max Range: 0.2037. Min Range: -0.2037

Max Act: 0.1550. Min Act: -0.0001

Data Index: 82017 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 0.2037. Min Range: -0.2037

Max Act: 0.1529. Min Act: -0.0001

Data Index: 1405095 (Python Code)

Max Activating Token Index: 44

Text #18

Max Range: 0.2037. Min Range: -0.2037

Max Act: 0.1521. Min Act: -0.0001

Data Index: 1623529 (Python Code)

Max Activating Token Index: 92

Text #19

Max Range: 0.2037. Min Range: -0.2037

Max Act: 0.1451. Min Act: -0.0001

Data Index: 475624 (C4 (Web Text))

Max Activating Token Index: 37