Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2082 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0868. Min Act: -0.0001

Data Index: 1584446 (Python Code)

Max Activating Token Index: 416

Text #1

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0700. Min Act: -0.0001

Data Index: 1468254 (Python Code)

Max Activating Token Index: 825

Text #2

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0725. Min Act: -0.0001

Data Index: 1092635 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0656. Min Act: -0.0001

Data Index: 1227508 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0681. Min Act: -0.0001

Data Index: 1415439 (Python Code)

Max Activating Token Index: 627

Text #5

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0635. Min Act: -0.0001

Data Index: 308264 (C4 (Web Text))

Max Activating Token Index: 935

Text #6

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0635. Min Act: -0.0001

Data Index: 659317 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0677. Min Act: -0.0001

Data Index: 587679 (C4 (Web Text))

Max Activating Token Index: 774

Text #8

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0615. Min Act: -0.0001

Data Index: 1509589 (Python Code)

Max Activating Token Index: 15

Text #9

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0646. Min Act: -0.0001

Data Index: 867871 (C4 (Web Text))

Max Activating Token Index: 259

Text #10

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0633. Min Act: -0.0001

Data Index: 244357 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0626. Min Act: -0.0001

Data Index: 751559 (C4 (Web Text))

Max Activating Token Index: 581

Text #12

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0625. Min Act: -0.0001

Data Index: 896375 (C4 (Web Text))

Max Activating Token Index: 663

Text #13

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0617. Min Act: -0.0002

Data Index: 261356 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0630. Min Act: -0.0001

Data Index: 387716 (C4 (Web Text))

Max Activating Token Index: 143

Text #15

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0577. Min Act: -0.0001

Data Index: 738789 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0592. Min Act: -0.0001

Data Index: 897345 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0591. Min Act: -0.0001

Data Index: 1132002 (C4 (Web Text))

Max Activating Token Index: 7

Text #18

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0590. Min Act: -0.0001

Data Index: 936006 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0586. Min Act: -0.0001

Data Index: 1134654 (C4 (Web Text))

Max Activating Token Index: 97