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

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

Neuron 1709 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: 0.2971. Min Range: -0.2971

Max Act: 0.2971. Min Act: -0.0002

Data Index: 1338581 (C4 (Web Text))

Max Activating Token Index: 830

Text #1

Max Range: 0.2971. Min Range: -0.2971

Max Act: 0.2917. Min Act: -0.0002

Data Index: 955920 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 0.2971. Min Range: -0.2971

Max Act: 0.2675. Min Act: -0.0002

Data Index: 960552 (C4 (Web Text))

Max Activating Token Index: 65

Text #3

Max Range: 0.2971. Min Range: -0.2971

Max Act: 0.2617. Min Act: -0.0001

Data Index: 1252725 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 0.2971. Min Range: -0.2971

Max Act: 0.2618. Min Act: -0.0002

Data Index: 808056 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 0.2971. Min Range: -0.2971

Max Act: 0.2509. Min Act: -0.0002

Data Index: 364993 (C4 (Web Text))

Max Activating Token Index: 27

Text #6

Max Range: 0.2971. Min Range: -0.2971

Max Act: 0.2588. Min Act: -0.0002

Data Index: 1252309 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 0.2971. Min Range: -0.2971

Max Act: 0.2549. Min Act: -0.0002

Data Index: 802474 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 0.2971. Min Range: -0.2971

Max Act: 0.2462. Min Act: -0.0002

Data Index: 37662 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 0.2971. Min Range: -0.2971

Max Act: 0.2548. Min Act: -0.0002

Data Index: 831203 (C4 (Web Text))

Max Activating Token Index: 205

Text #10

Max Range: 0.2971. Min Range: -0.2971

Max Act: 0.2531. Min Act: -0.0002

Data Index: 834917 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 0.2971. Min Range: -0.2971

Max Act: 0.2609. Min Act: -0.0002

Data Index: 220774 (C4 (Web Text))

Max Activating Token Index: 925

Text #12

Max Range: 0.2971. Min Range: -0.2971

Max Act: 0.2522. Min Act: -0.0002

Data Index: 517977 (C4 (Web Text))

Max Activating Token Index: 359

Text #13

Max Range: 0.2971. Min Range: -0.2971

Max Act: 0.2491. Min Act: -0.0002

Data Index: 682748 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 0.2971. Min Range: -0.2971

Max Act: 0.2558. Min Act: -0.0002

Data Index: 516606 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 0.2971. Min Range: -0.2971

Max Act: 0.2523. Min Act: -0.0002

Data Index: 2873 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 0.2971. Min Range: -0.2971

Max Act: 0.2547. Min Act: -0.0002

Data Index: 118197 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 0.2971. Min Range: -0.2971

Max Act: 0.2442. Min Act: -0.0002

Data Index: 122494 (C4 (Web Text))

Max Activating Token Index: 819

Text #18

Max Range: 0.2971. Min Range: -0.2971

Max Act: 0.2423. Min Act: -0.0002

Data Index: 411582 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 0.2971. Min Range: -0.2971

Max Act: 0.2526. Min Act: -0.0002

Data Index: 1316830 (C4 (Web Text))

Max Activating Token Index: 408