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

Dataset: The Pile

Neuron 2983 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: 0.7967. Min Range: -0.7967

Max Act: 0.7630. Min Act: -0.0001

Data Index: 1994594 (The Pile)

Max Activating Token Index: 583

Text #1

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7967. Min Act: -0.0000

Data Index: 732390 (The Pile)

Max Activating Token Index: 170

Text #2

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7346. Min Act: -0.0000

Data Index: 645143 (The Pile)

Max Activating Token Index: 79

Text #3

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7147. Min Act: -0.0000

Data Index: 163966 (The Pile)

Max Activating Token Index: 694

Text #4

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7856. Min Act: -0.0000

Data Index: 1582875 (The Pile)

Max Activating Token Index: 575

Text #5

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7770. Min Act: -0.0000

Data Index: 1430255 (The Pile)

Max Activating Token Index: 667

Text #6

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7600. Min Act: -0.0000

Data Index: 1215284 (The Pile)

Max Activating Token Index: 711

Text #7

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7188. Min Act: -0.0000

Data Index: 600967 (The Pile)

Max Activating Token Index: 518

Text #8

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7594. Min Act: -0.0000

Data Index: 1394150 (The Pile)

Max Activating Token Index: 178

Text #9

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7106. Min Act: -0.0000

Data Index: 158142 (The Pile)

Max Activating Token Index: 346

Text #10

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7310. Min Act: -0.0000

Data Index: 809220 (The Pile)

Max Activating Token Index: 843

Text #11

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7549. Min Act: -0.0000

Data Index: 1076809 (The Pile)

Max Activating Token Index: 546

Text #12

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7318. Min Act: -0.0000

Data Index: 1328166 (The Pile)

Max Activating Token Index: 630

Text #13

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7284. Min Act: -0.0000

Data Index: 306768 (The Pile)

Max Activating Token Index: 727

Text #14

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7702. Min Act: -0.0000

Data Index: 1689339 (The Pile)

Max Activating Token Index: 549

Text #15

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7224. Min Act: -0.0000

Data Index: 1864484 (The Pile)

Max Activating Token Index: 693

Text #16

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7047. Min Act: -0.0000

Data Index: 376472 (The Pile)

Max Activating Token Index: 680

Text #17

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7222. Min Act: -0.0000

Data Index: 332486 (The Pile)

Max Activating Token Index: 285

Text #18

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.6812. Min Act: -0.0000

Data Index: 1012346 (The Pile)

Max Activating Token Index: 933

Text #19

Max Range: 0.7967. Min Range: -0.7967

Max Act: 0.7012. Min Act: -0.0000

Data Index: 686950 (The Pile)

Max Activating Token Index: 588