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

Dataset: The Pile

Neuron 4035 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1776. Min Range: -7.1776

Max Act: 7.1776. Min Act: -0.0000

Data Index: 862023 (The Pile)

Max Activating Token Index: 422

Text #1

Max Range: 7.1776. Min Range: -7.1776

Max Act: 5.9563. Min Act: -0.0000

Data Index: 1363903 (The Pile)

Max Activating Token Index: 24

Text #2

Max Range: 7.1776. Min Range: -7.1776

Max Act: 5.4127. Min Act: -0.0000

Data Index: 1107091 (The Pile)

Max Activating Token Index: 280

Text #3

Max Range: 7.1776. Min Range: -7.1776

Max Act: 5.3578. Min Act: -0.0000

Data Index: 544592 (The Pile)

Max Activating Token Index: 276

Text #4

Max Range: 7.1776. Min Range: -7.1776

Max Act: 4.8578. Min Act: -0.0000

Data Index: 895419 (The Pile)

Max Activating Token Index: 806

Text #5

Max Range: 7.1776. Min Range: -7.1776

Max Act: 5.5519. Min Act: -0.0000

Data Index: 1778199 (The Pile)

Max Activating Token Index: 792

Text #6

Max Range: 7.1776. Min Range: -7.1776

Max Act: 4.1125. Min Act: -0.0000

Data Index: 1726821 (The Pile)

Max Activating Token Index: 556

Text #7

Max Range: 7.1776. Min Range: -7.1776

Max Act: 4.9960. Min Act: -0.0000

Data Index: 934235 (The Pile)

Max Activating Token Index: 808

Text #8

Max Range: 7.1776. Min Range: -7.1776

Max Act: 4.9276. Min Act: -0.0000

Data Index: 642134 (The Pile)

Max Activating Token Index: 691

Text #9

Max Range: 7.1776. Min Range: -7.1776

Max Act: 4.7373. Min Act: -0.0000

Data Index: 1941115 (The Pile)

Max Activating Token Index: 414

Text #10

Max Range: 7.1776. Min Range: -7.1776

Max Act: 4.6833. Min Act: -0.0000

Data Index: 1840906 (The Pile)

Max Activating Token Index: 404

Text #11

Max Range: 7.1776. Min Range: -7.1776

Max Act: 4.7081. Min Act: -0.0000

Data Index: 681026 (The Pile)

Max Activating Token Index: 657

Text #12

Max Range: 7.1776. Min Range: -7.1776

Max Act: 4.4719. Min Act: -0.0000

Data Index: 148344 (The Pile)

Max Activating Token Index: 827

Text #13

Max Range: 7.1776. Min Range: -7.1776

Max Act: 4.4166. Min Act: -0.0000

Data Index: 1962842 (The Pile)

Max Activating Token Index: 41

Text #14

Max Range: 7.1776. Min Range: -7.1776

Max Act: 4.7241. Min Act: -0.0000

Data Index: 1880271 (The Pile)

Max Activating Token Index: 813

Text #15

Max Range: 7.1776. Min Range: -7.1776

Max Act: 4.8961. Min Act: -0.0000

Data Index: 957492 (The Pile)

Max Activating Token Index: 51

Text #16

Max Range: 7.1776. Min Range: -7.1776

Max Act: 4.1679. Min Act: -0.0000

Data Index: 951124 (The Pile)

Max Activating Token Index: 656

Text #17

Max Range: 7.1776. Min Range: -7.1776

Max Act: 4.3817. Min Act: -0.0000

Data Index: 203185 (The Pile)

Max Activating Token Index: 1004

Text #18

Max Range: 7.1776. Min Range: -7.1776

Max Act: 4.2064. Min Act: -0.0000

Data Index: 607366 (The Pile)

Max Activating Token Index: 372

Text #19

Max Range: 7.1776. Min Range: -7.1776

Max Act: 4.3772. Min Act: -0.0000

Data Index: 24548 (The Pile)

Max Activating Token Index: 538