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

Dataset: The Pile

Neuron 1747 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1027. Min Range: -1.1027

Max Act: 1.1027. Min Act: -0.0000

Data Index: 131673 (The Pile)

Max Activating Token Index: 733

Text #1

Max Range: 1.1027. Min Range: -1.1027

Max Act: 1.0392. Min Act: -0.0000

Data Index: 285670 (The Pile)

Max Activating Token Index: 655

Text #2

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.9964. Min Act: -0.0000

Data Index: 437220 (The Pile)

Max Activating Token Index: 567

Text #3

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.9209. Min Act: -0.0000

Data Index: 1498708 (The Pile)

Max Activating Token Index: 858

Text #4

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.9483. Min Act: -0.0000

Data Index: 1355849 (The Pile)

Max Activating Token Index: 737

Text #5

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.9745. Min Act: -0.0000

Data Index: 1026686 (The Pile)

Max Activating Token Index: 660

Text #6

Max Range: 1.1027. Min Range: -1.1027

Max Act: 1.0002. Min Act: -0.0000

Data Index: 1361101 (The Pile)

Max Activating Token Index: 736

Text #7

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.9571. Min Act: -0.0000

Data Index: 1123275 (The Pile)

Max Activating Token Index: 272

Text #8

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.9279. Min Act: -0.0000

Data Index: 1827448 (The Pile)

Max Activating Token Index: 689

Text #9

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.9844. Min Act: -0.0000

Data Index: 1088230 (The Pile)

Max Activating Token Index: 489

Text #10

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.9589. Min Act: -0.0000

Data Index: 1295513 (The Pile)

Max Activating Token Index: 673

Text #11

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.8709. Min Act: -0.0000

Data Index: 1968724 (The Pile)

Max Activating Token Index: 358

Text #12

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.9808. Min Act: -0.0000

Data Index: 1401542 (The Pile)

Max Activating Token Index: 869

Text #13

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.8841. Min Act: -0.0000

Data Index: 512767 (The Pile)

Max Activating Token Index: 439

Text #14

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.9416. Min Act: -0.0000

Data Index: 1298919 (The Pile)

Max Activating Token Index: 107

Text #15

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.8722. Min Act: -0.0000

Data Index: 1158483 (The Pile)

Max Activating Token Index: 471

Text #16

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.8812. Min Act: -0.0000

Data Index: 78205 (The Pile)

Max Activating Token Index: 679

Text #17

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.8672. Min Act: -0.0000

Data Index: 1205962 (The Pile)

Max Activating Token Index: 111

Text #18

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.8402. Min Act: -0.0000

Data Index: 1669338 (The Pile)

Max Activating Token Index: 378

Text #19

Max Range: 1.1027. Min Range: -1.1027

Max Act: 0.9095. Min Act: -0.0000

Data Index: 1566546 (The Pile)

Max Activating Token Index: 291