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

Dataset: The Pile

Neuron 663 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: 0.9985. Min Range: -0.9985

Max Act: 0.9985. Min Act: -0.0000

Data Index: 328864 (The Pile)

Max Activating Token Index: 685

Text #1

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.7302. Min Act: -0.0000

Data Index: 1979782 (The Pile)

Max Activating Token Index: 734

Text #2

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.7710. Min Act: -0.0000

Data Index: 1192952 (The Pile)

Max Activating Token Index: 1006

Text #3

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.7358. Min Act: -0.0000

Data Index: 957643 (The Pile)

Max Activating Token Index: 888

Text #4

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.7014. Min Act: -0.0000

Data Index: 1092778 (The Pile)

Max Activating Token Index: 165

Text #5

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.7221. Min Act: -0.0000

Data Index: 28821 (The Pile)

Max Activating Token Index: 985

Text #6

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.6954. Min Act: -0.0000

Data Index: 1996072 (The Pile)

Max Activating Token Index: 951

Text #7

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.7358. Min Act: -0.0000

Data Index: 298904 (The Pile)

Max Activating Token Index: 708

Text #8

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.6745. Min Act: -0.0000

Data Index: 1576743 (The Pile)

Max Activating Token Index: 750

Text #9

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.6518. Min Act: -0.0000

Data Index: 665133 (The Pile)

Max Activating Token Index: 507

Text #10

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.6686. Min Act: -0.0000

Data Index: 377841 (The Pile)

Max Activating Token Index: 636

Text #11

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.7445. Min Act: -0.0000

Data Index: 1487004 (The Pile)

Max Activating Token Index: 760

Text #12

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.6627. Min Act: -0.0000

Data Index: 859403 (The Pile)

Max Activating Token Index: 136

Text #13

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.6857. Min Act: -0.0000

Data Index: 793301 (The Pile)

Max Activating Token Index: 803

Text #14

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.7204. Min Act: -0.0000

Data Index: 1099195 (The Pile)

Max Activating Token Index: 786

Text #15

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.6648. Min Act: -0.0000

Data Index: 1353364 (The Pile)

Max Activating Token Index: 73

Text #16

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.7024. Min Act: -0.0000

Data Index: 625839 (The Pile)

Max Activating Token Index: 766

Text #17

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.6568. Min Act: -0.0000

Data Index: 827241 (The Pile)

Max Activating Token Index: 893

Text #18

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.6409. Min Act: -0.0000

Data Index: 1516119 (The Pile)

Max Activating Token Index: 722

Text #19

Max Range: 0.9985. Min Range: -0.9985

Max Act: 0.5970. Min Act: -0.0000

Data Index: 642122 (The Pile)

Max Activating Token Index: 465