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

Dataset: The Pile

Neuron 1767 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: 1.8809. Min Range: -1.8809

Max Act: 1.8809. Min Act: -0.0000

Data Index: 38107 (The Pile)

Max Activating Token Index: 972

Text #1

Max Range: 1.8809. Min Range: -1.8809

Max Act: 1.1459. Min Act: -0.0000

Data Index: 1441460 (The Pile)

Max Activating Token Index: 1014

Text #2

Max Range: 1.8809. Min Range: -1.8809

Max Act: 1.0683. Min Act: -0.0000

Data Index: 1088082 (The Pile)

Max Activating Token Index: 502

Text #3

Max Range: 1.8809. Min Range: -1.8809

Max Act: 1.0891. Min Act: -0.0000

Data Index: 1323578 (The Pile)

Max Activating Token Index: 765

Text #4

Max Range: 1.8809. Min Range: -1.8809

Max Act: 0.8836. Min Act: -0.0000

Data Index: 1338858 (The Pile)

Max Activating Token Index: 488

Text #5

Max Range: 1.8809. Min Range: -1.8809

Max Act: 0.8541. Min Act: -0.0000

Data Index: 1720192 (The Pile)

Max Activating Token Index: 213

Text #6

Max Range: 1.8809. Min Range: -1.8809

Max Act: 0.8402. Min Act: -0.0000

Data Index: 288630 (The Pile)

Max Activating Token Index: 986

Text #7

Max Range: 1.8809. Min Range: -1.8809

Max Act: 0.8633. Min Act: -0.0000

Data Index: 1991260 (The Pile)

Max Activating Token Index: 150

Text #8

Max Range: 1.8809. Min Range: -1.8809

Max Act: 0.9147. Min Act: -0.0000

Data Index: 997190 (The Pile)

Max Activating Token Index: 504

Text #9

Max Range: 1.8809. Min Range: -1.8809

Max Act: 0.7433. Min Act: -0.0000

Data Index: 692247 (The Pile)

Max Activating Token Index: 15

Text #10

Max Range: 1.8809. Min Range: -1.8809

Max Act: 0.7852. Min Act: -0.0000

Data Index: 1454887 (The Pile)

Max Activating Token Index: 852

Text #11

Max Range: 1.8809. Min Range: -1.8809

Max Act: 0.8062. Min Act: -0.0000

Data Index: 1525662 (The Pile)

Max Activating Token Index: 853

Text #12

Max Range: 1.8809. Min Range: -1.8809

Max Act: 0.8029. Min Act: -0.0000

Data Index: 1084665 (The Pile)

Max Activating Token Index: 775

Text #13

Max Range: 1.8809. Min Range: -1.8809

Max Act: 0.8531. Min Act: -0.0000

Data Index: 197034 (The Pile)

Max Activating Token Index: 891

Text #14

Max Range: 1.8809. Min Range: -1.8809

Max Act: 0.7942. Min Act: -0.0000

Data Index: 769658 (The Pile)

Max Activating Token Index: 517

Text #15

Max Range: 1.8809. Min Range: -1.8809

Max Act: 0.7618. Min Act: -0.0000

Data Index: 528356 (The Pile)

Max Activating Token Index: 843

Text #16

Max Range: 1.8809. Min Range: -1.8809

Max Act: 0.7838. Min Act: -0.0000

Data Index: 1850163 (The Pile)

Max Activating Token Index: 22

Text #17

Max Range: 1.8809. Min Range: -1.8809

Max Act: 0.8287. Min Act: -0.0000

Data Index: 818952 (The Pile)

Max Activating Token Index: 635

Text #18

Max Range: 1.8809. Min Range: -1.8809

Max Act: 0.7727. Min Act: -0.0000

Data Index: 1408817 (The Pile)

Max Activating Token Index: 806

Text #19

Max Range: 1.8809. Min Range: -1.8809

Max Act: 0.8215. Min Act: -0.0000

Data Index: 310844 (The Pile)

Max Activating Token Index: 851