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

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

Neuron 2706 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0583. Min Act: -0.0002

Data Index: 52793 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0573. Min Act: -0.0003

Data Index: 859595 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0534. Min Act: -0.0002

Data Index: 104546 (C4 (Web Text))

Max Activating Token Index: 111

Text #3

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0498. Min Act: -0.0003

Data Index: 42575 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0468. Min Act: -0.0003

Data Index: 382200 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0431. Min Act: -0.0003

Data Index: 70711 (C4 (Web Text))

Max Activating Token Index: 324

Text #6

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0495. Min Act: -0.0003

Data Index: 204120 (C4 (Web Text))

Max Activating Token Index: 689

Text #7

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0411. Min Act: -0.0002

Data Index: 1303649 (C4 (Web Text))

Max Activating Token Index: 696

Text #8

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0445. Min Act: -0.0003

Data Index: 1183381 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0409. Min Act: -0.0002

Data Index: 195862 (C4 (Web Text))

Max Activating Token Index: 103

Text #10

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0432. Min Act: -0.0002

Data Index: 541031 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0420. Min Act: -0.0003

Data Index: 1196587 (C4 (Web Text))

Max Activating Token Index: 890

Text #12

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0425. Min Act: -0.0002

Data Index: 310547 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0401. Min Act: -0.0002

Data Index: 1096036 (C4 (Web Text))

Max Activating Token Index: 257

Text #14

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0433. Min Act: -0.0003

Data Index: 40447 (C4 (Web Text))

Max Activating Token Index: 691

Text #15

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0408. Min Act: -0.0003

Data Index: 210621 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0422. Min Act: -0.0002

Data Index: 1061435 (C4 (Web Text))

Max Activating Token Index: 343

Text #17

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1220628 (C4 (Web Text))

Max Activating Token Index: 961

Text #18

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0401. Min Act: -0.0003

Data Index: 1358895 (C4 (Web Text))

Max Activating Token Index: 508

Text #19

Max Range: 0.0583. Min Range: -0.0583

Max Act: 0.0393. Min Act: -0.0002

Data Index: 1358933 (C4 (Web Text))

Max Activating Token Index: 791