Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3860 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.3009. Min Act: -0.0000

Data Index: 987998 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.2687. Min Act: -0.0000

Data Index: 969213 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.2709. Min Act: -0.0000

Data Index: 726003 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.2408. Min Act: -0.0000

Data Index: 963778 (C4 (Web Text))

Max Activating Token Index: 510

Text #4

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.2042. Min Act: -0.0000

Data Index: 286906 (C4 (Web Text))

Max Activating Token Index: 811

Text #5

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.1969. Min Act: -0.0000

Data Index: 300816 (C4 (Web Text))

Max Activating Token Index: 540

Text #6

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.1698. Min Act: -0.0000

Data Index: 1249203 (C4 (Web Text))

Max Activating Token Index: 772

Text #7

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.1942. Min Act: -0.0001

Data Index: 414539 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.1800. Min Act: -0.0000

Data Index: 290652 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.1660. Min Act: -0.0000

Data Index: 395671 (C4 (Web Text))

Max Activating Token Index: 620

Text #10

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.1833. Min Act: -0.0000

Data Index: 233094 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.1632. Min Act: -0.0000

Data Index: 573479 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.1825. Min Act: -0.0000

Data Index: 550000 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.1533. Min Act: -0.0000

Data Index: 7241 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.1516. Min Act: -0.0000

Data Index: 216597 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.1507. Min Act: -0.0000

Data Index: 10287 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.1521. Min Act: -0.0000

Data Index: 426336 (C4 (Web Text))

Max Activating Token Index: 184

Text #17

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.1604. Min Act: -0.0000

Data Index: 159323 (C4 (Web Text))

Max Activating Token Index: 49

Text #18

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.1448. Min Act: -0.0000

Data Index: 464278 (C4 (Web Text))

Max Activating Token Index: 847

Text #19

Max Range: 0.3009. Min Range: -0.3009

Max Act: 0.1614. Min Act: -0.0001

Data Index: 4873 (C4 (Web Text))

Max Activating Token Index: 141