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

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

Neuron 280 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: 0.0595. Min Range: -0.0595

Max Act: 0.0595. Min Act: -0.0003

Data Index: 366775 (C4 (Web Text))

Max Activating Token Index: 216

Text #1

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0576. Min Act: -0.0003

Data Index: 1047531 (C4 (Web Text))

Max Activating Token Index: 607

Text #2

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0552. Min Act: -0.0003

Data Index: 159843 (C4 (Web Text))

Max Activating Token Index: 973

Text #3

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0534. Min Act: -0.0003

Data Index: 169688 (C4 (Web Text))

Max Activating Token Index: 593

Text #4

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0564. Min Act: -0.0003

Data Index: 394132 (C4 (Web Text))

Max Activating Token Index: 861

Text #5

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0571. Min Act: -0.0002

Data Index: 383479 (C4 (Web Text))

Max Activating Token Index: 636

Text #6

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0525. Min Act: -0.0003

Data Index: 301759 (C4 (Web Text))

Max Activating Token Index: 224

Text #7

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0543. Min Act: -0.0003

Data Index: 434677 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0521. Min Act: -0.0003

Data Index: 80602 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0539. Min Act: -0.0003

Data Index: 605802 (C4 (Web Text))

Max Activating Token Index: 856

Text #10

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0515. Min Act: -0.0004

Data Index: 1033877 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0517. Min Act: -0.0002

Data Index: 842152 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0529. Min Act: -0.0003

Data Index: 1424892 (Python Code)

Max Activating Token Index: 540

Text #13

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0521. Min Act: -0.0003

Data Index: 1077139 (C4 (Web Text))

Max Activating Token Index: 719

Text #14

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0534. Min Act: -0.0003

Data Index: 988629 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0535. Min Act: -0.0003

Data Index: 172083 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0518. Min Act: -0.0003

Data Index: 357488 (C4 (Web Text))

Max Activating Token Index: 80

Text #17

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0531. Min Act: -0.0003

Data Index: 230254 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0495. Min Act: -0.0003

Data Index: 1371420 (Python Code)

Max Activating Token Index: 631

Text #19

Max Range: 0.0595. Min Range: -0.0595

Max Act: 0.0510. Min Act: -0.0003

Data Index: 852742 (C4 (Web Text))

Max Activating Token Index: 678