Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 435 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0752. Min Act: -0.0002

Data Index: 341201 (C4 (Web Text))

Max Activating Token Index: 941

Text #1

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0749. Min Act: -0.0003

Data Index: 79026 (C4 (Web Text))

Max Activating Token Index: 304

Text #2

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0711. Min Act: -0.0004

Data Index: 836046 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0670. Min Act: -0.0003

Data Index: 188359 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0681. Min Act: -0.0004

Data Index: 1288854 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0652. Min Act: -0.0003

Data Index: 548691 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0628. Min Act: -0.0003

Data Index: 975642 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0615. Min Act: -0.0003

Data Index: 69369 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0619. Min Act: -0.0004

Data Index: 1201265 (C4 (Web Text))

Max Activating Token Index: 32

Text #9

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0617. Min Act: -0.0003

Data Index: 976618 (C4 (Web Text))

Max Activating Token Index: 335

Text #10

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0606. Min Act: -0.0003

Data Index: 842649 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0617. Min Act: -0.0003

Data Index: 1166090 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0593. Min Act: -0.0003

Data Index: 1048777 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0586. Min Act: -0.0003

Data Index: 56251 (C4 (Web Text))

Max Activating Token Index: 479

Text #14

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0569. Min Act: -0.0003

Data Index: 405955 (C4 (Web Text))

Max Activating Token Index: 397

Text #15

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0593. Min Act: -0.0003

Data Index: 1032036 (C4 (Web Text))

Max Activating Token Index: 731

Text #16

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0570. Min Act: -0.0003

Data Index: 32957 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0563. Min Act: -0.0004

Data Index: 26008 (C4 (Web Text))

Max Activating Token Index: 675

Text #18

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0569. Min Act: -0.0003

Data Index: 892892 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 0.0752. Min Range: -0.0752

Max Act: 0.0572. Min Act: -0.0003

Data Index: 159604 (C4 (Web Text))

Max Activating Token Index: 533