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

Dataset: The Pile

Neuron 350 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.8984. Min Act: -0.0000

Data Index: 549924 (The Pile)

Max Activating Token Index: 906

Text #1

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.8539. Min Act: -0.0000

Data Index: 601803 (The Pile)

Max Activating Token Index: 217

Text #2

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7652. Min Act: -0.0000

Data Index: 17409 (The Pile)

Max Activating Token Index: 458

Text #3

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.8571. Min Act: -0.0000

Data Index: 1959987 (The Pile)

Max Activating Token Index: 478

Text #4

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7826. Min Act: -0.0000

Data Index: 493710 (The Pile)

Max Activating Token Index: 405

Text #5

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7449. Min Act: -0.0000

Data Index: 510613 (The Pile)

Max Activating Token Index: 886

Text #6

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7893. Min Act: -0.0000

Data Index: 32207 (The Pile)

Max Activating Token Index: 848

Text #7

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7163. Min Act: -0.0000

Data Index: 1288925 (The Pile)

Max Activating Token Index: 213

Text #8

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.6862. Min Act: -0.0000

Data Index: 536753 (The Pile)

Max Activating Token Index: 926

Text #9

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.6187. Min Act: -0.0000

Data Index: 911329 (The Pile)

Max Activating Token Index: 798

Text #10

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.6598. Min Act: -0.0000

Data Index: 1662097 (The Pile)

Max Activating Token Index: 762

Text #11

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.6796. Min Act: -0.0000

Data Index: 417252 (The Pile)

Max Activating Token Index: 457

Text #12

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.6526. Min Act: -0.0000

Data Index: 652946 (The Pile)

Max Activating Token Index: 887

Text #13

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7045. Min Act: -0.0000

Data Index: 1601500 (The Pile)

Max Activating Token Index: 432

Text #14

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.6623. Min Act: -0.0000

Data Index: 1468728 (The Pile)

Max Activating Token Index: 208

Text #15

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.6740. Min Act: -0.0000

Data Index: 301393 (The Pile)

Max Activating Token Index: 833

Text #16

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.5880. Min Act: -0.0000

Data Index: 525406 (The Pile)

Max Activating Token Index: 793

Text #17

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.6537. Min Act: -0.0000

Data Index: 1581911 (The Pile)

Max Activating Token Index: 451

Text #18

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.7001. Min Act: -0.0000

Data Index: 1923237 (The Pile)

Max Activating Token Index: 933

Text #19

Max Range: 0.8984. Min Range: -0.8984

Max Act: 0.6175. Min Act: -0.0000

Data Index: 1228103 (The Pile)

Max Activating Token Index: 912