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

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

Neuron 4803 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: 0.1759. Min Range: -0.1759

Max Act: 0.1759. Min Act: -0.0000

Data Index: 830922 (C4 (Web Text))

Max Activating Token Index: 658

Text #1

Max Range: 0.1759. Min Range: -0.1759

Max Act: 0.1672. Min Act: -0.0000

Data Index: 121772 (C4 (Web Text))

Max Activating Token Index: 567

Text #2

Max Range: 0.1759. Min Range: -0.1759

Max Act: 0.1690. Min Act: -0.0000

Data Index: 178196 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 0.1759. Min Range: -0.1759

Max Act: 0.1564. Min Act: -0.0000

Data Index: 628065 (C4 (Web Text))

Max Activating Token Index: 719

Text #4

Max Range: 0.1759. Min Range: -0.1759

Max Act: 0.1555. Min Act: -0.0000

Data Index: 458869 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 0.1759. Min Range: -0.1759

Max Act: 0.1605. Min Act: -0.0000

Data Index: 257147 (C4 (Web Text))

Max Activating Token Index: 394

Text #6

Max Range: 0.1759. Min Range: -0.1759

Max Act: 0.1568. Min Act: -0.0000

Data Index: 664684 (C4 (Web Text))

Max Activating Token Index: 612

Text #7

Max Range: 0.1759. Min Range: -0.1759

Max Act: 0.1508. Min Act: -0.0000

Data Index: 1017424 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 0.1759. Min Range: -0.1759

Max Act: 0.1540. Min Act: -0.0000

Data Index: 20468 (C4 (Web Text))

Max Activating Token Index: 776

Text #9

Max Range: 0.1759. Min Range: -0.1759

Max Act: 0.1374. Min Act: -0.0000

Data Index: 871393 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 0.1759. Min Range: -0.1759

Max Act: 0.1513. Min Act: -0.0000

Data Index: 1331862 (C4 (Web Text))

Max Activating Token Index: 618

Text #11

Max Range: 0.1759. Min Range: -0.1759

Max Act: 0.1503. Min Act: -0.0000

Data Index: 757269 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 0.1759. Min Range: -0.1759

Max Act: 0.1349. Min Act: -0.0000

Data Index: 1071894 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 0.1759. Min Range: -0.1759

Max Act: 0.1420. Min Act: -0.0000

Data Index: 208292 (C4 (Web Text))

Max Activating Token Index: 645

Text #14

Max Range: 0.1759. Min Range: -0.1759

Max Act: 0.1308. Min Act: -0.0000

Data Index: 866082 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 0.1759. Min Range: -0.1759

Max Act: 0.1369. Min Act: -0.0000

Data Index: 1109188 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 0.1759. Min Range: -0.1759

Max Act: 0.1357. Min Act: -0.0000

Data Index: 324828 (C4 (Web Text))

Max Activating Token Index: 241

Text #17

Max Range: 0.1759. Min Range: -0.1759

Max Act: 0.1306. Min Act: -0.0000

Data Index: 896688 (C4 (Web Text))

Max Activating Token Index: 584

Text #18

Max Range: 0.1759. Min Range: -0.1759

Max Act: 0.1317. Min Act: -0.0000

Data Index: 1352916 (C4 (Web Text))

Max Activating Token Index: 179

Text #19

Max Range: 0.1759. Min Range: -0.1759

Max Act: 0.1318. Min Act: -0.0000

Data Index: 880582 (C4 (Web Text))

Max Activating Token Index: 556