Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 250 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0692. Min Act: -0.0002

Data Index: 484276 (C4 (Web Text))

Max Activating Token Index: 788

Text #1

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0698. Min Act: -0.0002

Data Index: 1197700 (C4 (Web Text))

Max Activating Token Index: 105

Text #2

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0690. Min Act: -0.0002

Data Index: 161744 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0662. Min Act: -0.0002

Data Index: 29427 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0652. Min Act: -0.0002

Data Index: 954496 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0654. Min Act: -0.0002

Data Index: 1204083 (C4 (Web Text))

Max Activating Token Index: 413

Text #6

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0651. Min Act: -0.0002

Data Index: 525851 (C4 (Web Text))

Max Activating Token Index: 629

Text #7

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0602. Min Act: -0.0002

Data Index: 374607 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0630. Min Act: -0.0002

Data Index: 754987 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0638. Min Act: -0.0002

Data Index: 1057215 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0613. Min Act: -0.0002

Data Index: 1347647 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0619. Min Act: -0.0002

Data Index: 405519 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0575. Min Act: -0.0002

Data Index: 1195678 (C4 (Web Text))

Max Activating Token Index: 426

Text #13

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0601. Min Act: -0.0002

Data Index: 136565 (C4 (Web Text))

Max Activating Token Index: 848

Text #14

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0595. Min Act: -0.0002

Data Index: 987624 (C4 (Web Text))

Max Activating Token Index: 508

Text #15

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0603. Min Act: -0.0002

Data Index: 1003913 (C4 (Web Text))

Max Activating Token Index: 177

Text #16

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0594. Min Act: -0.0002

Data Index: 715062 (C4 (Web Text))

Max Activating Token Index: 605

Text #17

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0589. Min Act: -0.0002

Data Index: 598300 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0567. Min Act: -0.0002

Data Index: 480950 (C4 (Web Text))

Max Activating Token Index: 867

Text #19

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0595. Min Act: -0.0002

Data Index: 157854 (C4 (Web Text))

Max Activating Token Index: 743