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

Dataset: The Pile

Neuron 2400 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: 1.2831. Min Range: -1.2831

Max Act: 1.2687. Min Act: -0.0000

Data Index: 1180113 (The Pile)

Max Activating Token Index: 435

Text #1

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.2269. Min Act: -0.0000

Data Index: 545915 (The Pile)

Max Activating Token Index: 904

Text #2

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.2831. Min Act: -0.0000

Data Index: 1091085 (The Pile)

Max Activating Token Index: 785

Text #3

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.2107. Min Act: -0.0000

Data Index: 837980 (The Pile)

Max Activating Token Index: 113

Text #4

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.2033. Min Act: -0.0000

Data Index: 1841253 (The Pile)

Max Activating Token Index: 1005

Text #5

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.1784. Min Act: -0.0000

Data Index: 1290714 (The Pile)

Max Activating Token Index: 256

Text #6

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.1477. Min Act: -0.0000

Data Index: 311501 (The Pile)

Max Activating Token Index: 811

Text #7

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.2052. Min Act: -0.0000

Data Index: 1002725 (The Pile)

Max Activating Token Index: 980

Text #8

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.1777. Min Act: -0.0000

Data Index: 532145 (The Pile)

Max Activating Token Index: 542

Text #9

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.1896. Min Act: -0.0000

Data Index: 425379 (The Pile)

Max Activating Token Index: 1017

Text #10

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.2111. Min Act: -0.0000

Data Index: 1650698 (The Pile)

Max Activating Token Index: 746

Text #11

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.1752. Min Act: -0.0000

Data Index: 15401 (The Pile)

Max Activating Token Index: 220

Text #12

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.1660. Min Act: -0.0000

Data Index: 1461739 (The Pile)

Max Activating Token Index: 976

Text #13

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.1304. Min Act: -0.0000

Data Index: 1854673 (The Pile)

Max Activating Token Index: 151

Text #14

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.0690. Min Act: -0.0000

Data Index: 124418 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.1750. Min Act: -0.0000

Data Index: 747806 (The Pile)

Max Activating Token Index: 429

Text #16

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.1096. Min Act: -0.0000

Data Index: 687222 (The Pile)

Max Activating Token Index: 1000

Text #17

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.1376. Min Act: -0.0000

Data Index: 77641 (The Pile)

Max Activating Token Index: 201

Text #18

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.0722. Min Act: -0.0000

Data Index: 267316 (The Pile)

Max Activating Token Index: 58

Text #19

Max Range: 1.2831. Min Range: -1.2831

Max Act: 1.2052. Min Act: -0.0000

Data Index: 304538 (The Pile)

Max Activating Token Index: 980