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

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

Neuron 3778 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0800. Min Act: -0.0002

Data Index: 209706 (C4 (Web Text))

Max Activating Token Index: 432

Text #1

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0790. Min Act: -0.0002

Data Index: 737475 (C4 (Web Text))

Max Activating Token Index: 151

Text #2

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0757. Min Act: -0.0002

Data Index: 632798 (C4 (Web Text))

Max Activating Token Index: 709

Text #3

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0786. Min Act: -0.0002

Data Index: 1027857 (C4 (Web Text))

Max Activating Token Index: 93

Text #4

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0747. Min Act: -0.0002

Data Index: 458639 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0713. Min Act: -0.0002

Data Index: 406797 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0674. Min Act: -0.0002

Data Index: 157143 (C4 (Web Text))

Max Activating Token Index: 450

Text #7

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0667. Min Act: -0.0002

Data Index: 1328895 (C4 (Web Text))

Max Activating Token Index: 653

Text #8

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0686. Min Act: -0.0002

Data Index: 1219895 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0671. Min Act: -0.0002

Data Index: 478655 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0668. Min Act: -0.0002

Data Index: 722575 (C4 (Web Text))

Max Activating Token Index: 231

Text #11

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0670. Min Act: -0.0002

Data Index: 803722 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0656. Min Act: -0.0002

Data Index: 1207364 (C4 (Web Text))

Max Activating Token Index: 582

Text #13

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0683. Min Act: -0.0002

Data Index: 1201849 (C4 (Web Text))

Max Activating Token Index: 353

Text #14

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0656. Min Act: -0.0002

Data Index: 1108575 (C4 (Web Text))

Max Activating Token Index: 8

Text #15

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0633. Min Act: -0.0002

Data Index: 583991 (C4 (Web Text))

Max Activating Token Index: 987

Text #16

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0606. Min Act: -0.0002

Data Index: 978622 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0628. Min Act: -0.0002

Data Index: 667915 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0615. Min Act: -0.0002

Data Index: 92755 (C4 (Web Text))

Max Activating Token Index: 260

Text #19

Max Range: 0.0800. Min Range: -0.0800

Max Act: 0.0588. Min Act: -0.0002

Data Index: 109366 (C4 (Web Text))

Max Activating Token Index: 172