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

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

Neuron 2171 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0482. Min Range: -2.0482

Max Act: 2.0482. Min Act: -0.0000

Data Index: 803921 (C4 (Web Text))

Max Activating Token Index: 655

Text #1

Max Range: 2.0482. Min Range: -2.0482

Max Act: 1.8333. Min Act: -0.0000

Data Index: 1244687 (C4 (Web Text))

Max Activating Token Index: 23

Text #2

Max Range: 2.0482. Min Range: -2.0482

Max Act: 1.7765. Min Act: -0.0000

Data Index: 1351552 (C4 (Web Text))

Max Activating Token Index: 266

Text #3

Max Range: 2.0482. Min Range: -2.0482

Max Act: 1.7618. Min Act: -0.0000

Data Index: 195587 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 2.0482. Min Range: -2.0482

Max Act: 1.6224. Min Act: -0.0000

Data Index: 1154262 (C4 (Web Text))

Max Activating Token Index: 956

Text #5

Max Range: 2.0482. Min Range: -2.0482

Max Act: 1.6792. Min Act: -0.0000

Data Index: 560892 (C4 (Web Text))

Max Activating Token Index: 198

Text #6

Max Range: 2.0482. Min Range: -2.0482

Max Act: 1.6395. Min Act: -0.0000

Data Index: 656868 (C4 (Web Text))

Max Activating Token Index: 988

Text #7

Max Range: 2.0482. Min Range: -2.0482

Max Act: 1.6346. Min Act: -0.0000

Data Index: 1186822 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 2.0482. Min Range: -2.0482

Max Act: 1.6252. Min Act: -0.0000

Data Index: 874972 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 2.0482. Min Range: -2.0482

Max Act: 1.6103. Min Act: -0.0000

Data Index: 376796 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 2.0482. Min Range: -2.0482

Max Act: 1.5856. Min Act: -0.0000

Data Index: 1271854 (C4 (Web Text))

Max Activating Token Index: 565

Text #11

Max Range: 2.0482. Min Range: -2.0482

Max Act: 1.4820. Min Act: -0.0000

Data Index: 854267 (C4 (Web Text))

Max Activating Token Index: 191

Text #12

Max Range: 2.0482. Min Range: -2.0482

Max Act: 1.5002. Min Act: -0.0000

Data Index: 1245527 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 2.0482. Min Range: -2.0482

Max Act: 1.4860. Min Act: -0.0000

Data Index: 939037 (C4 (Web Text))

Max Activating Token Index: 213

Text #14

Max Range: 2.0482. Min Range: -2.0482

Max Act: 1.4866. Min Act: -0.0000

Data Index: 936724 (C4 (Web Text))

Max Activating Token Index: 915

Text #15

Max Range: 2.0482. Min Range: -2.0482

Max Act: 1.4625. Min Act: -0.0000

Data Index: 1219516 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 2.0482. Min Range: -2.0482

Max Act: 1.4501. Min Act: -0.0000

Data Index: 1136131 (C4 (Web Text))

Max Activating Token Index: 724

Text #17

Max Range: 2.0482. Min Range: -2.0482

Max Act: 1.5270. Min Act: -0.0000

Data Index: 180943 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 2.0482. Min Range: -2.0482

Max Act: 1.3436. Min Act: -0.0000

Data Index: 313668 (C4 (Web Text))

Max Activating Token Index: 797

Text #19

Max Range: 2.0482. Min Range: -2.0482

Max Act: 1.5893. Min Act: -0.0000

Data Index: 105739 (C4 (Web Text))

Max Activating Token Index: 292