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

Dataset: The Pile

Neuron 1827 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: 1.1727. Min Range: -1.1727

Max Act: 1.1727. Min Act: -0.0000

Data Index: 943172 (The Pile)

Max Activating Token Index: 955

Text #1

Max Range: 1.1727. Min Range: -1.1727

Max Act: 1.0438. Min Act: -0.0000

Data Index: 1804798 (The Pile)

Max Activating Token Index: 765

Text #2

Max Range: 1.1727. Min Range: -1.1727

Max Act: 1.1087. Min Act: -0.0000

Data Index: 874224 (The Pile)

Max Activating Token Index: 741

Text #3

Max Range: 1.1727. Min Range: -1.1727

Max Act: 1.0060. Min Act: -0.0000

Data Index: 653320 (The Pile)

Max Activating Token Index: 350

Text #4

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.9826. Min Act: -0.0000

Data Index: 1050668 (The Pile)

Max Activating Token Index: 877

Text #5

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.8515. Min Act: -0.0000

Data Index: 1167306 (The Pile)

Max Activating Token Index: 746

Text #6

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.8069. Min Act: -0.0000

Data Index: 1005674 (The Pile)

Max Activating Token Index: 756

Text #7

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.7597. Min Act: -0.0000

Data Index: 1656293 (The Pile)

Max Activating Token Index: 150

Text #8

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.7397. Min Act: -0.0000

Data Index: 106103 (The Pile)

Max Activating Token Index: 798

Text #9

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.7194. Min Act: -0.0000

Data Index: 70559 (The Pile)

Max Activating Token Index: 912

Text #10

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.6952. Min Act: -0.0000

Data Index: 1335203 (The Pile)

Max Activating Token Index: 500

Text #11

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.8095. Min Act: -0.0000

Data Index: 1760724 (The Pile)

Max Activating Token Index: 804

Text #12

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.6838. Min Act: -0.0000

Data Index: 1976324 (The Pile)

Max Activating Token Index: 941

Text #13

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.6868. Min Act: -0.0000

Data Index: 1513179 (The Pile)

Max Activating Token Index: 816

Text #14

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.6676. Min Act: -0.0000

Data Index: 50209 (The Pile)

Max Activating Token Index: 154

Text #15

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.6418. Min Act: -0.0000

Data Index: 1340665 (The Pile)

Max Activating Token Index: 932

Text #16

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.6683. Min Act: 0.0000

Data Index: 252450 (The Pile)

Max Activating Token Index: 779

Text #17

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.6756. Min Act: -0.0000

Data Index: 1412499 (The Pile)

Max Activating Token Index: 330

Text #18

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.6495. Min Act: -0.0000

Data Index: 703010 (The Pile)

Max Activating Token Index: 300

Text #19

Max Range: 1.1727. Min Range: -1.1727

Max Act: 0.6479. Min Act: -0.0000

Data Index: 1193830 (The Pile)

Max Activating Token Index: 105