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

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

Neuron 2512 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0861. Min Act: -0.0000

Data Index: 955566 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0776. Min Act: -0.0000

Data Index: 1205870 (C4 (Web Text))

Max Activating Token Index: 549

Text #2

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0774. Min Act: -0.0000

Data Index: 1384166 (Python Code)

Max Activating Token Index: 744

Text #3

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0710. Min Act: -0.0000

Data Index: 102312 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0731. Min Act: -0.0000

Data Index: 375041 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0706. Min Act: -0.0000

Data Index: 1651825 (Python Code)

Max Activating Token Index: 379

Text #6

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0682. Min Act: -0.0000

Data Index: 1162769 (C4 (Web Text))

Max Activating Token Index: 636

Text #7

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0689. Min Act: -0.0000

Data Index: 818286 (C4 (Web Text))

Max Activating Token Index: 748

Text #8

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0657. Min Act: -0.0000

Data Index: 618715 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0637. Min Act: -0.0000

Data Index: 1329900 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0631. Min Act: -0.0000

Data Index: 955340 (C4 (Web Text))

Max Activating Token Index: 710

Text #11

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0636. Min Act: -0.0000

Data Index: 697219 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0628. Min Act: -0.0000

Data Index: 339311 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0593. Min Act: -0.0000

Data Index: 1359073 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0595. Min Act: -0.0000

Data Index: 332879 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0625. Min Act: -0.0000

Data Index: 495058 (C4 (Web Text))

Max Activating Token Index: 446

Text #16

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0582. Min Act: -0.0000

Data Index: 269804 (C4 (Web Text))

Max Activating Token Index: 464

Text #17

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0566. Min Act: -0.0000

Data Index: 994784 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0611. Min Act: -0.0000

Data Index: 1076729 (C4 (Web Text))

Max Activating Token Index: 732

Text #19

Max Range: 0.0861. Min Range: -0.0861

Max Act: 0.0606. Min Act: -0.0000

Data Index: 314621 (C4 (Web Text))

Max Activating Token Index: 362