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

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

Neuron 3941 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: 0.2479. Min Range: -0.2479

Max Act: 0.2479. Min Act: -0.0001

Data Index: 1321820 (C4 (Web Text))

Max Activating Token Index: 210

Text #1

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.2160. Min Act: -0.0001

Data Index: 5878 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.2111. Min Act: -0.0001

Data Index: 10284 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.1966. Min Act: -0.0000

Data Index: 408454 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.1953. Min Act: -0.0001

Data Index: 1283800 (C4 (Web Text))

Max Activating Token Index: 900

Text #5

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.1857. Min Act: -0.0001

Data Index: 1020505 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.1811. Min Act: -0.0001

Data Index: 840032 (C4 (Web Text))

Max Activating Token Index: 98

Text #7

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.1734. Min Act: -0.0001

Data Index: 880700 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.1806. Min Act: -0.0001

Data Index: 348598 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.1712. Min Act: -0.0000

Data Index: 1263939 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.1661. Min Act: -0.0001

Data Index: 602 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.1717. Min Act: -0.0001

Data Index: 1425522 (Python Code)

Max Activating Token Index: 612

Text #12

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.1712. Min Act: -0.0000

Data Index: 864945 (C4 (Web Text))

Max Activating Token Index: 958

Text #13

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.1640. Min Act: -0.0001

Data Index: 1067798 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.1744. Min Act: -0.0001

Data Index: 303999 (C4 (Web Text))

Max Activating Token Index: 20

Text #15

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.1681. Min Act: -0.0001

Data Index: 1256459 (C4 (Web Text))

Max Activating Token Index: 992

Text #16

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.1656. Min Act: -0.0001

Data Index: 1591 (C4 (Web Text))

Max Activating Token Index: 300

Text #17

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.1618. Min Act: -0.0001

Data Index: 1275514 (C4 (Web Text))

Max Activating Token Index: 961

Text #18

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.1485. Min Act: -0.0001

Data Index: 826596 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 0.2479. Min Range: -0.2479

Max Act: 0.1594. Min Act: -0.0000

Data Index: 1066777 (C4 (Web Text))

Max Activating Token Index: 414