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

Dataset: The Pile

Neuron 746 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: 1.1424. Min Range: -1.1424

Max Act: 1.1424. Min Act: -0.0000

Data Index: 698309 (The Pile)

Max Activating Token Index: 604

Text #1

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.9390. Min Act: -0.0000

Data Index: 1767041 (The Pile)

Max Activating Token Index: 92

Text #2

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.8846. Min Act: -0.0000

Data Index: 1780853 (The Pile)

Max Activating Token Index: 537

Text #3

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.8355. Min Act: -0.0000

Data Index: 1775063 (The Pile)

Max Activating Token Index: 357

Text #4

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.8595. Min Act: -0.0000

Data Index: 1199554 (The Pile)

Max Activating Token Index: 534

Text #5

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.8673. Min Act: -0.0000

Data Index: 722031 (The Pile)

Max Activating Token Index: 352

Text #6

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.8651. Min Act: -0.0000

Data Index: 194885 (The Pile)

Max Activating Token Index: 292

Text #7

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.8531. Min Act: -0.0000

Data Index: 1471494 (The Pile)

Max Activating Token Index: 662

Text #8

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.8434. Min Act: -0.0000

Data Index: 1307386 (The Pile)

Max Activating Token Index: 643

Text #9

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.8035. Min Act: -0.0000

Data Index: 450141 (The Pile)

Max Activating Token Index: 304

Text #10

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.7293. Min Act: -0.0000

Data Index: 1638411 (The Pile)

Max Activating Token Index: 933

Text #11

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.8070. Min Act: -0.0000

Data Index: 172784 (The Pile)

Max Activating Token Index: 659

Text #12

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.7443. Min Act: -0.0000

Data Index: 70219 (The Pile)

Max Activating Token Index: 710

Text #13

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.8027. Min Act: -0.0000

Data Index: 1600241 (The Pile)

Max Activating Token Index: 1016

Text #14

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.7061. Min Act: -0.0000

Data Index: 1776781 (The Pile)

Max Activating Token Index: 583

Text #15

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.7888. Min Act: -0.0000

Data Index: 1340637 (The Pile)

Max Activating Token Index: 880

Text #16

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.6997. Min Act: -0.0000

Data Index: 279879 (The Pile)

Max Activating Token Index: 805

Text #17

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.8777. Min Act: -0.0000

Data Index: 1612993 (The Pile)

Max Activating Token Index: 703

Text #18

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.7154. Min Act: -0.0000

Data Index: 937886 (The Pile)

Max Activating Token Index: 717

Text #19

Max Range: 1.1424. Min Range: -1.1424

Max Act: 0.7089. Min Act: -0.0000

Data Index: 1951047 (The Pile)

Max Activating Token Index: 1006