Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1325 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1778. Min Act: -0.0003

Data Index: 973401 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1829. Min Act: -0.0003

Data Index: 1021187 (C4 (Web Text))

Max Activating Token Index: 386

Text #2

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1667. Min Act: -0.0003

Data Index: 952815 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1625. Min Act: -0.0002

Data Index: 271918 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1615. Min Act: -0.0003

Data Index: 585591 (C4 (Web Text))

Max Activating Token Index: 1011

Text #5

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1678. Min Act: -0.0003

Data Index: 783141 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1670. Min Act: -0.0003

Data Index: 1320072 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1403. Min Act: -0.0003

Data Index: 117387 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1521. Min Act: -0.0003

Data Index: 625657 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1453. Min Act: -0.0003

Data Index: 132136 (C4 (Web Text))

Max Activating Token Index: 567

Text #10

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1478. Min Act: -0.0003

Data Index: 1349937 (C4 (Web Text))

Max Activating Token Index: 217

Text #11

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1471. Min Act: -0.0003

Data Index: 274746 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1433. Min Act: -0.0003

Data Index: 1203248 (C4 (Web Text))

Max Activating Token Index: 880

Text #13

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1531. Min Act: -0.0003

Data Index: 371525 (C4 (Web Text))

Max Activating Token Index: 675

Text #14

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1472. Min Act: -0.0003

Data Index: 1237154 (C4 (Web Text))

Max Activating Token Index: 820

Text #15

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1441. Min Act: -0.0003

Data Index: 372222 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1361. Min Act: -0.0003

Data Index: 967317 (C4 (Web Text))

Max Activating Token Index: 424

Text #17

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1421. Min Act: -0.0002

Data Index: 621656 (C4 (Web Text))

Max Activating Token Index: 466

Text #18

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1395. Min Act: -0.0003

Data Index: 1064210 (C4 (Web Text))

Max Activating Token Index: 868

Text #19

Max Range: 0.1829. Min Range: -0.1829

Max Act: 0.1338. Min Act: -0.0003

Data Index: 357562 (C4 (Web Text))

Max Activating Token Index: 1021