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

Dataset: The Pile

Neuron 4139 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5901. Min Range: -5.5901

Max Act: 5.5901. Min Act: -0.0000

Data Index: 1270809 (The Pile)

Max Activating Token Index: 291

Text #1

Max Range: 5.5901. Min Range: -5.5901

Max Act: 4.5930. Min Act: -0.0000

Data Index: 1216061 (The Pile)

Max Activating Token Index: 248

Text #2

Max Range: 5.5901. Min Range: -5.5901

Max Act: 4.7894. Min Act: -0.0000

Data Index: 386263 (The Pile)

Max Activating Token Index: 971

Text #3

Max Range: 5.5901. Min Range: -5.5901

Max Act: 4.6266. Min Act: -0.0000

Data Index: 861396 (The Pile)

Max Activating Token Index: 830

Text #4

Max Range: 5.5901. Min Range: -5.5901

Max Act: 4.1455. Min Act: -0.0000

Data Index: 668180 (The Pile)

Max Activating Token Index: 846

Text #5

Max Range: 5.5901. Min Range: -5.5901

Max Act: 3.8645. Min Act: -0.0000

Data Index: 1304971 (The Pile)

Max Activating Token Index: 993

Text #6

Max Range: 5.5901. Min Range: -5.5901

Max Act: 4.0817. Min Act: -0.0000

Data Index: 1096602 (The Pile)

Max Activating Token Index: 730

Text #7

Max Range: 5.5901. Min Range: -5.5901

Max Act: 3.9922. Min Act: -0.0000

Data Index: 212447 (The Pile)

Max Activating Token Index: 659

Text #8

Max Range: 5.5901. Min Range: -5.5901

Max Act: 3.8231. Min Act: -0.0000

Data Index: 1869123 (The Pile)

Max Activating Token Index: 660

Text #9

Max Range: 5.5901. Min Range: -5.5901

Max Act: 3.7554. Min Act: -0.0000

Data Index: 1203914 (The Pile)

Max Activating Token Index: 973

Text #10

Max Range: 5.5901. Min Range: -5.5901

Max Act: 3.4401. Min Act: -0.0000

Data Index: 346694 (The Pile)

Max Activating Token Index: 470

Text #11

Max Range: 5.5901. Min Range: -5.5901

Max Act: 3.4852. Min Act: -0.0000

Data Index: 132099 (The Pile)

Max Activating Token Index: 1013

Text #12

Max Range: 5.5901. Min Range: -5.5901

Max Act: 3.6873. Min Act: -0.0000

Data Index: 1066240 (The Pile)

Max Activating Token Index: 767

Text #13

Max Range: 5.5901. Min Range: -5.5901

Max Act: 3.4782. Min Act: -0.0000

Data Index: 679045 (The Pile)

Max Activating Token Index: 481

Text #14

Max Range: 5.5901. Min Range: -5.5901

Max Act: 3.1508. Min Act: -0.0000

Data Index: 604868 (The Pile)

Max Activating Token Index: 224

Text #15

Max Range: 5.5901. Min Range: -5.5901

Max Act: 3.1740. Min Act: -0.0000

Data Index: 569732 (The Pile)

Max Activating Token Index: 374

Text #16

Max Range: 5.5901. Min Range: -5.5901

Max Act: 3.4363. Min Act: -0.0000

Data Index: 74960 (The Pile)

Max Activating Token Index: 1005

Text #17

Max Range: 5.5901. Min Range: -5.5901

Max Act: 3.4390. Min Act: -0.0000

Data Index: 216403 (The Pile)

Max Activating Token Index: 919

Text #18

Max Range: 5.5901. Min Range: -5.5901

Max Act: 3.2807. Min Act: -0.0000

Data Index: 987307 (The Pile)

Max Activating Token Index: 794

Text #19

Max Range: 5.5901. Min Range: -5.5901

Max Act: 3.5431. Min Act: -0.0000

Data Index: 1328903 (The Pile)

Max Activating Token Index: 502