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

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

Neuron 4872 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1960. Min Act: -0.0001

Data Index: 92954 (C4 (Web Text))

Max Activating Token Index: 905

Text #1

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1855. Min Act: -0.0000

Data Index: 721654 (C4 (Web Text))

Max Activating Token Index: 477

Text #2

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1940. Min Act: -0.0001

Data Index: 546579 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1874. Min Act: -0.0001

Data Index: 599998 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1839. Min Act: -0.0001

Data Index: 879702 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1749. Min Act: -0.0001

Data Index: 1229518 (C4 (Web Text))

Max Activating Token Index: 469

Text #6

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1752. Min Act: -0.0000

Data Index: 662481 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1668. Min Act: -0.0001

Data Index: 438415 (C4 (Web Text))

Max Activating Token Index: 824

Text #8

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1746. Min Act: -0.0001

Data Index: 459621 (C4 (Web Text))

Max Activating Token Index: 361

Text #9

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1756. Min Act: -0.0001

Data Index: 286861 (C4 (Web Text))

Max Activating Token Index: 851

Text #10

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1585. Min Act: -0.0001

Data Index: 1069796 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1570. Min Act: -0.0001

Data Index: 60061 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1719. Min Act: -0.0001

Data Index: 595556 (C4 (Web Text))

Max Activating Token Index: 956

Text #13

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1555. Min Act: -0.0000

Data Index: 154695 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1566. Min Act: -0.0001

Data Index: 756920 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1625. Min Act: -0.0000

Data Index: 756423 (C4 (Web Text))

Max Activating Token Index: 392

Text #16

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1628. Min Act: -0.0001

Data Index: 1327280 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1521. Min Act: -0.0001

Data Index: 1197895 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1360. Min Act: -0.0001

Data Index: 658878 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 0.1960. Min Range: -0.1960

Max Act: 0.1570. Min Act: -0.0000

Data Index: 804061 (C4 (Web Text))

Max Activating Token Index: 328