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

Dataset: The Pile

Neuron 3521 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0685. Min Range: -1.0685

Max Act: 1.0685. Min Act: -0.0000

Data Index: 1058342 (The Pile)

Max Activating Token Index: 904

Text #1

Max Range: 1.0685. Min Range: -1.0685

Max Act: 0.9901. Min Act: -0.0000

Data Index: 112035 (The Pile)

Max Activating Token Index: 768

Text #2

Max Range: 1.0685. Min Range: -1.0685

Max Act: 0.9338. Min Act: -0.0000

Data Index: 740349 (The Pile)

Max Activating Token Index: 604

Text #3

Max Range: 1.0685. Min Range: -1.0685

Max Act: 1.0407. Min Act: -0.0000

Data Index: 1479192 (The Pile)

Max Activating Token Index: 776

Text #4

Max Range: 1.0685. Min Range: -1.0685

Max Act: 0.9678. Min Act: -0.0000

Data Index: 1781170 (The Pile)

Max Activating Token Index: 930

Text #5

Max Range: 1.0685. Min Range: -1.0685

Max Act: 0.9650. Min Act: -0.0000

Data Index: 1527785 (The Pile)

Max Activating Token Index: 605

Text #6

Max Range: 1.0685. Min Range: -1.0685

Max Act: 0.9181. Min Act: -0.0000

Data Index: 960123 (The Pile)

Max Activating Token Index: 886

Text #7

Max Range: 1.0685. Min Range: -1.0685

Max Act: 0.9899. Min Act: -0.0000

Data Index: 215425 (The Pile)

Max Activating Token Index: 783

Text #8

Max Range: 1.0685. Min Range: -1.0685

Max Act: 0.8564. Min Act: -0.0000

Data Index: 1021551 (The Pile)

Max Activating Token Index: 28

Text #9

Max Range: 1.0685. Min Range: -1.0685

Max Act: 0.9831. Min Act: -0.0000

Data Index: 684939 (The Pile)

Max Activating Token Index: 26

Text #10

Max Range: 1.0685. Min Range: -1.0685

Max Act: 0.9000. Min Act: -0.0000

Data Index: 1697813 (The Pile)

Max Activating Token Index: 1012

Text #11

Max Range: 1.0685. Min Range: -1.0685

Max Act: 0.9654. Min Act: -0.0000

Data Index: 94597 (The Pile)

Max Activating Token Index: 770

Text #12

Max Range: 1.0685. Min Range: -1.0685

Max Act: 0.8786. Min Act: -0.0000

Data Index: 1238531 (The Pile)

Max Activating Token Index: 631

Text #13

Max Range: 1.0685. Min Range: -1.0685

Max Act: 0.9267. Min Act: -0.0000

Data Index: 518259 (The Pile)

Max Activating Token Index: 767

Text #14

Max Range: 1.0685. Min Range: -1.0685

Max Act: 0.8348. Min Act: -0.0000

Data Index: 512840 (The Pile)

Max Activating Token Index: 591

Text #15

Max Range: 1.0685. Min Range: -1.0685

Max Act: 0.8789. Min Act: -0.0000

Data Index: 971971 (The Pile)

Max Activating Token Index: 965

Text #16

Max Range: 1.0685. Min Range: -1.0685

Max Act: 0.9015. Min Act: -0.0000

Data Index: 765450 (The Pile)

Max Activating Token Index: 703

Text #17

Max Range: 1.0685. Min Range: -1.0685

Max Act: 0.9160. Min Act: -0.0000

Data Index: 301350 (The Pile)

Max Activating Token Index: 232

Text #18

Max Range: 1.0685. Min Range: -1.0685

Max Act: 0.8243. Min Act: -0.0000

Data Index: 1546155 (The Pile)

Max Activating Token Index: 971

Text #19

Max Range: 1.0685. Min Range: -1.0685

Max Act: 0.8961. Min Act: -0.0000

Data Index: 1890354 (The Pile)

Max Activating Token Index: 623