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

Dataset: The Pile

Neuron 3879 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: 1.4573. Min Range: -1.4573

Max Act: 1.4573. Min Act: -0.0000

Data Index: 1607317 (The Pile)

Max Activating Token Index: 400

Text #1

Max Range: 1.4573. Min Range: -1.4573

Max Act: 0.9215. Min Act: -0.0000

Data Index: 190335 (The Pile)

Max Activating Token Index: 754

Text #2

Max Range: 1.4573. Min Range: -1.4573

Max Act: 0.9550. Min Act: -0.0000

Data Index: 1028898 (The Pile)

Max Activating Token Index: 671

Text #3

Max Range: 1.4573. Min Range: -1.4573

Max Act: 0.8386. Min Act: -0.0000

Data Index: 443502 (The Pile)

Max Activating Token Index: 735

Text #4

Max Range: 1.4573. Min Range: -1.4573

Max Act: 0.8243. Min Act: -0.0000

Data Index: 177269 (The Pile)

Max Activating Token Index: 427

Text #5

Max Range: 1.4573. Min Range: -1.4573

Max Act: 0.7745. Min Act: -0.0000

Data Index: 126281 (The Pile)

Max Activating Token Index: 962

Text #6

Max Range: 1.4573. Min Range: -1.4573

Max Act: 0.7590. Min Act: -0.0000

Data Index: 154134 (The Pile)

Max Activating Token Index: 499

Text #7

Max Range: 1.4573. Min Range: -1.4573

Max Act: 0.6715. Min Act: -0.0000

Data Index: 1417926 (The Pile)

Max Activating Token Index: 812

Text #8

Max Range: 1.4573. Min Range: -1.4573

Max Act: 0.6669. Min Act: -0.0000

Data Index: 1218540 (The Pile)

Max Activating Token Index: 757

Text #9

Max Range: 1.4573. Min Range: -1.4573

Max Act: 0.7563. Min Act: -0.0000

Data Index: 958217 (The Pile)

Max Activating Token Index: 998

Text #10

Max Range: 1.4573. Min Range: -1.4573

Max Act: 0.6337. Min Act: -0.0000

Data Index: 140143 (The Pile)

Max Activating Token Index: 467

Text #11

Max Range: 1.4573. Min Range: -1.4573

Max Act: 0.5514. Min Act: -0.0000

Data Index: 1666967 (The Pile)

Max Activating Token Index: 955

Text #12

Max Range: 1.4573. Min Range: -1.4573

Max Act: 0.6224. Min Act: -0.0000

Data Index: 625764 (The Pile)

Max Activating Token Index: 111

Text #13

Max Range: 1.4573. Min Range: -1.4573

Max Act: 0.6198. Min Act: -0.0000

Data Index: 65563 (The Pile)

Max Activating Token Index: 571

Text #14

Max Range: 1.4573. Min Range: -1.4573

Max Act: 0.5337. Min Act: -0.0000

Data Index: 303317 (The Pile)

Max Activating Token Index: 747

Text #15

Max Range: 1.4573. Min Range: -1.4573

Max Act: 0.5871. Min Act: -0.0000

Data Index: 1562506 (The Pile)

Max Activating Token Index: 668

Text #16

Max Range: 1.4573. Min Range: -1.4573

Max Act: 0.5743. Min Act: -0.0000

Data Index: 437023 (The Pile)

Max Activating Token Index: 537

Text #17

Max Range: 1.4573. Min Range: -1.4573

Max Act: 0.6439. Min Act: -0.0000

Data Index: 663366 (The Pile)

Max Activating Token Index: 502

Text #18

Max Range: 1.4573. Min Range: -1.4573

Max Act: 0.6256. Min Act: -0.0000

Data Index: 947154 (The Pile)

Max Activating Token Index: 570

Text #19

Max Range: 1.4573. Min Range: -1.4573

Max Act: 0.6752. Min Act: -0.0000

Data Index: 648876 (The Pile)

Max Activating Token Index: 1019