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

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

Neuron 3913 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1590. Min Range: -2.1590

Max Act: 2.1590. Min Act: -0.0000

Data Index: 908970 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 2.1590. Min Range: -2.1590

Max Act: 1.2941. Min Act: -0.0000

Data Index: 1154142 (C4 (Web Text))

Max Activating Token Index: 329

Text #2

Max Range: 2.1590. Min Range: -2.1590

Max Act: 1.5102. Min Act: -0.0000

Data Index: 296965 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 2.1590. Min Range: -2.1590

Max Act: 1.4059. Min Act: -0.0000

Data Index: 771218 (C4 (Web Text))

Max Activating Token Index: 855

Text #4

Max Range: 2.1590. Min Range: -2.1590

Max Act: 1.5171. Min Act: -0.0000

Data Index: 1231512 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 2.1590. Min Range: -2.1590

Max Act: 1.4013. Min Act: -0.0000

Data Index: 963499 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 2.1590. Min Range: -2.1590

Max Act: 1.3013. Min Act: -0.0000

Data Index: 1043376 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 2.1590. Min Range: -2.1590

Max Act: 1.2355. Min Act: -0.0000

Data Index: 1233722 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 2.1590. Min Range: -2.1590

Max Act: 1.2311. Min Act: -0.0000

Data Index: 247742 (C4 (Web Text))

Max Activating Token Index: 349

Text #9

Max Range: 2.1590. Min Range: -2.1590

Max Act: 1.1409. Min Act: -0.0000

Data Index: 87224 (C4 (Web Text))

Max Activating Token Index: 132

Text #10

Max Range: 2.1590. Min Range: -2.1590

Max Act: 1.2034. Min Act: -0.0000

Data Index: 1214407 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 2.1590. Min Range: -2.1590

Max Act: 1.1273. Min Act: -0.0000

Data Index: 709122 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 2.1590. Min Range: -2.1590

Max Act: 1.1857. Min Act: -0.0000

Data Index: 1232168 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 2.1590. Min Range: -2.1590

Max Act: 1.1814. Min Act: -0.0000

Data Index: 484625 (C4 (Web Text))

Max Activating Token Index: 382

Text #14

Max Range: 2.1590. Min Range: -2.1590

Max Act: 1.1080. Min Act: -0.0000

Data Index: 1048673 (C4 (Web Text))

Max Activating Token Index: 317

Text #15

Max Range: 2.1590. Min Range: -2.1590

Max Act: 1.1678. Min Act: -0.0000

Data Index: 262641 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 2.1590. Min Range: -2.1590

Max Act: 1.0694. Min Act: -0.0000

Data Index: 838944 (C4 (Web Text))

Max Activating Token Index: 962

Text #17

Max Range: 2.1590. Min Range: -2.1590

Max Act: 1.1210. Min Act: -0.0000

Data Index: 520473 (C4 (Web Text))

Max Activating Token Index: 295

Text #18

Max Range: 2.1590. Min Range: -2.1590

Max Act: 1.1917. Min Act: -0.0000

Data Index: 328657 (C4 (Web Text))

Max Activating Token Index: 983

Text #19

Max Range: 2.1590. Min Range: -2.1590

Max Act: 1.1165. Min Act: -0.0000

Data Index: 654734 (C4 (Web Text))

Max Activating Token Index: 653