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

Dataset: The Pile

Neuron 1141 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0783. Min Range: -1.0783

Max Act: 1.0783. Min Act: -0.0000

Data Index: 1637798 (The Pile)

Max Activating Token Index: 604

Text #1

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.7588. Min Act: -0.0000

Data Index: 1816081 (The Pile)

Max Activating Token Index: 1010

Text #2

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.6862. Min Act: -0.0000

Data Index: 1810950 (The Pile)

Max Activating Token Index: 679

Text #3

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.6899. Min Act: -0.0000

Data Index: 1051888 (The Pile)

Max Activating Token Index: 865

Text #4

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.5971. Min Act: -0.0000

Data Index: 1923221 (The Pile)

Max Activating Token Index: 621

Text #5

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.5332. Min Act: -0.0000

Data Index: 1645724 (The Pile)

Max Activating Token Index: 585

Text #6

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.5146. Min Act: -0.0000

Data Index: 585133 (The Pile)

Max Activating Token Index: 755

Text #7

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.5029. Min Act: -0.0000

Data Index: 467004 (The Pile)

Max Activating Token Index: 439

Text #8

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.5216. Min Act: -0.0000

Data Index: 592814 (The Pile)

Max Activating Token Index: 386

Text #9

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.4760. Min Act: -0.0000

Data Index: 1315386 (The Pile)

Max Activating Token Index: 666

Text #10

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.4672. Min Act: -0.0000

Data Index: 1900605 (The Pile)

Max Activating Token Index: 879

Text #11

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.4171. Min Act: -0.0000

Data Index: 1573373 (The Pile)

Max Activating Token Index: 383

Text #12

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.4404. Min Act: -0.0000

Data Index: 1642225 (The Pile)

Max Activating Token Index: 860

Text #13

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.4274. Min Act: -0.0000

Data Index: 21473 (The Pile)

Max Activating Token Index: 1009

Text #14

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.4786. Min Act: -0.0000

Data Index: 1134031 (The Pile)

Max Activating Token Index: 65

Text #15

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.4023. Min Act: -0.0000

Data Index: 461863 (The Pile)

Max Activating Token Index: 823

Text #16

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.4664. Min Act: 0.0000

Data Index: 1151322 (The Pile)

Max Activating Token Index: 148

Text #17

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.4510. Min Act: -0.0000

Data Index: 1983957 (The Pile)

Max Activating Token Index: 596

Text #18

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.4185. Min Act: -0.0000

Data Index: 411064 (The Pile)

Max Activating Token Index: 1022

Text #19

Max Range: 1.0783. Min Range: -1.0783

Max Act: 0.4153. Min Act: -0.0000

Data Index: 869086 (The Pile)

Max Activating Token Index: 1010