Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3004 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0701. Min Act: -0.0002

Data Index: 576809 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0727. Min Act: -0.0002

Data Index: 493281 (C4 (Web Text))

Max Activating Token Index: 890

Text #2

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0678. Min Act: -0.0002

Data Index: 347496 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0671. Min Act: -0.0002

Data Index: 607873 (C4 (Web Text))

Max Activating Token Index: 681

Text #4

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0630. Min Act: -0.0003

Data Index: 1082509 (C4 (Web Text))

Max Activating Token Index: 170

Text #5

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0671. Min Act: -0.0002

Data Index: 1316072 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0693. Min Act: -0.0002

Data Index: 185738 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0666. Min Act: -0.0002

Data Index: 1079923 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0630. Min Act: -0.0002

Data Index: 1032536 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0617. Min Act: -0.0002

Data Index: 884988 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0643. Min Act: -0.0002

Data Index: 1176704 (C4 (Web Text))

Max Activating Token Index: 67

Text #11

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0612. Min Act: -0.0002

Data Index: 1281786 (C4 (Web Text))

Max Activating Token Index: 542

Text #12

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0645. Min Act: -0.0002

Data Index: 305495 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0615. Min Act: -0.0002

Data Index: 534820 (C4 (Web Text))

Max Activating Token Index: 809

Text #14

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0621. Min Act: -0.0003

Data Index: 779437 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0624. Min Act: -0.0002

Data Index: 602903 (C4 (Web Text))

Max Activating Token Index: 41

Text #16

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0613. Min Act: -0.0003

Data Index: 452424 (C4 (Web Text))

Max Activating Token Index: 568

Text #17

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0643. Min Act: -0.0002

Data Index: 1273905 (C4 (Web Text))

Max Activating Token Index: 360

Text #18

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0623. Min Act: -0.0002

Data Index: 605053 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 0.0727. Min Range: -0.0727

Max Act: 0.0620. Min Act: -0.0002

Data Index: 749603 (C4 (Web Text))

Max Activating Token Index: 710