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

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

Neuron 5081 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2406. Min Act: -0.0000

Data Index: 513942 (C4 (Web Text))

Max Activating Token Index: 630

Text #1

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2121. Min Act: -0.0000

Data Index: 817403 (C4 (Web Text))

Max Activating Token Index: 193

Text #2

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2140. Min Act: -0.0000

Data Index: 1027188 (C4 (Web Text))

Max Activating Token Index: 913

Text #3

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.2003. Min Act: -0.0000

Data Index: 1266308 (C4 (Web Text))

Max Activating Token Index: 440

Text #4

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1969. Min Act: -0.0000

Data Index: 1188800 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1828. Min Act: -0.0000

Data Index: 450973 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1784. Min Act: -0.0000

Data Index: 1080708 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1626. Min Act: -0.0000

Data Index: 452033 (C4 (Web Text))

Max Activating Token Index: 888

Text #8

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1684. Min Act: -0.0000

Data Index: 451895 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1722. Min Act: -0.0000

Data Index: 895317 (C4 (Web Text))

Max Activating Token Index: 159

Text #10

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1720. Min Act: -0.0000

Data Index: 395150 (C4 (Web Text))

Max Activating Token Index: 848

Text #11

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1622. Min Act: -0.0000

Data Index: 834997 (C4 (Web Text))

Max Activating Token Index: 48

Text #12

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1681. Min Act: -0.0000

Data Index: 839013 (C4 (Web Text))

Max Activating Token Index: 908

Text #13

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1565. Min Act: -0.0000

Data Index: 133965 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1631. Min Act: -0.0000

Data Index: 48823 (C4 (Web Text))

Max Activating Token Index: 403

Text #15

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1674. Min Act: -0.0000

Data Index: 551279 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1558. Min Act: -0.0000

Data Index: 1285352 (C4 (Web Text))

Max Activating Token Index: 959

Text #17

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1544. Min Act: -0.0000

Data Index: 105784 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1608. Min Act: -0.0000

Data Index: 1298492 (C4 (Web Text))

Max Activating Token Index: 485

Text #19

Max Range: 0.2406. Min Range: -0.2406

Max Act: 0.1600. Min Act: -0.0000

Data Index: 849596 (C4 (Web Text))

Max Activating Token Index: 97