Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1280 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.9854. Min Act: -0.0000

Data Index: 444399 (The Pile)

Max Activating Token Index: 703

Text #1

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.9611. Min Act: -0.0000

Data Index: 1986293 (The Pile)

Max Activating Token Index: 581

Text #2

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.9893. Min Act: -0.0000

Data Index: 207918 (The Pile)

Max Activating Token Index: 793

Text #3

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.9736. Min Act: -0.0000

Data Index: 160776 (The Pile)

Max Activating Token Index: 493

Text #4

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.9190. Min Act: -0.0000

Data Index: 1870780 (The Pile)

Max Activating Token Index: 924

Text #5

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8912. Min Act: -0.0000

Data Index: 1776203 (The Pile)

Max Activating Token Index: 827

Text #6

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8594. Min Act: -0.0000

Data Index: 1202800 (The Pile)

Max Activating Token Index: 462

Text #7

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8500. Min Act: -0.0000

Data Index: 355609 (The Pile)

Max Activating Token Index: 561

Text #8

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.9119. Min Act: -0.0000

Data Index: 1807717 (The Pile)

Max Activating Token Index: 998

Text #9

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8730. Min Act: -0.0000

Data Index: 1538197 (The Pile)

Max Activating Token Index: 506

Text #10

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8687. Min Act: -0.0000

Data Index: 1496154 (The Pile)

Max Activating Token Index: 622

Text #11

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8693. Min Act: -0.0000

Data Index: 782302 (The Pile)

Max Activating Token Index: 911

Text #12

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8567. Min Act: -0.0000

Data Index: 666766 (The Pile)

Max Activating Token Index: 512

Text #13

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8837. Min Act: -0.0000

Data Index: 811063 (The Pile)

Max Activating Token Index: 549

Text #14

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8686. Min Act: -0.0000

Data Index: 294733 (The Pile)

Max Activating Token Index: 267

Text #15

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8607. Min Act: -0.0000

Data Index: 57682 (The Pile)

Max Activating Token Index: 861

Text #16

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8253. Min Act: -0.0000

Data Index: 872257 (The Pile)

Max Activating Token Index: 743

Text #17

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8790. Min Act: -0.0000

Data Index: 860891 (The Pile)

Max Activating Token Index: 1009

Text #18

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.8163. Min Act: -0.0000

Data Index: 728839 (The Pile)

Max Activating Token Index: 168

Text #19

Max Range: 0.9893. Min Range: -0.9893

Max Act: 0.7884. Min Act: -0.0000

Data Index: 1649940 (The Pile)

Max Activating Token Index: 974