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

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

Neuron 1073 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0763. Min Act: -0.0000

Data Index: 32176 (C4 (Web Text))

Max Activating Token Index: 431

Text #1

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0683. Min Act: -0.0001

Data Index: 631412 (C4 (Web Text))

Max Activating Token Index: 724

Text #2

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0786. Min Act: -0.0001

Data Index: 843871 (C4 (Web Text))

Max Activating Token Index: 231

Text #3

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0678. Min Act: -0.0001

Data Index: 750068 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0733. Min Act: -0.0001

Data Index: 293873 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0702. Min Act: -0.0001

Data Index: 108819 (C4 (Web Text))

Max Activating Token Index: 215

Text #6

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0736. Min Act: -0.0001

Data Index: 329447 (C4 (Web Text))

Max Activating Token Index: 69

Text #7

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0796. Min Act: -0.0000

Data Index: 1080353 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0721. Min Act: -0.0000

Data Index: 1319411 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0753. Min Act: -0.0001

Data Index: 793486 (C4 (Web Text))

Max Activating Token Index: 24

Text #10

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0723. Min Act: -0.0001

Data Index: 1092878 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0696. Min Act: -0.0001

Data Index: 248026 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0685. Min Act: -0.0000

Data Index: 598269 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0728. Min Act: -0.0001

Data Index: 599114 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0685. Min Act: -0.0001

Data Index: 684786 (C4 (Web Text))

Max Activating Token Index: 937

Text #15

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0661. Min Act: -0.0001

Data Index: 1217828 (C4 (Web Text))

Max Activating Token Index: 822

Text #16

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0621. Min Act: -0.0001

Data Index: 552600 (C4 (Web Text))

Max Activating Token Index: 733

Text #17

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0615. Min Act: -0.0001

Data Index: 859399 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0639. Min Act: -0.0000

Data Index: 779982 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 0.0796. Min Range: -0.0796

Max Act: 0.0667. Min Act: -0.0001

Data Index: 98859 (C4 (Web Text))

Max Activating Token Index: 763