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

Dataset: The Pile

Neuron 1744 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.9527. Min Act: -0.0000

Data Index: 1897537 (The Pile)

Max Activating Token Index: 1016

Text #1

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.8855. Min Act: -0.0000

Data Index: 1819536 (The Pile)

Max Activating Token Index: 137

Text #2

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.8167. Min Act: -0.0000

Data Index: 470327 (The Pile)

Max Activating Token Index: 715

Text #3

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.9066. Min Act: -0.0000

Data Index: 47488 (The Pile)

Max Activating Token Index: 466

Text #4

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.7362. Min Act: -0.0000

Data Index: 623617 (The Pile)

Max Activating Token Index: 574

Text #5

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.6556. Min Act: -0.0000

Data Index: 1567327 (The Pile)

Max Activating Token Index: 636

Text #6

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.6716. Min Act: -0.0000

Data Index: 812128 (The Pile)

Max Activating Token Index: 466

Text #7

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.7654. Min Act: -0.0000

Data Index: 1242380 (The Pile)

Max Activating Token Index: 529

Text #8

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.5184. Min Act: -0.0000

Data Index: 1343361 (The Pile)

Max Activating Token Index: 719

Text #9

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.6948. Min Act: -0.0000

Data Index: 78746 (The Pile)

Max Activating Token Index: 327

Text #10

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.5754. Min Act: -0.0000

Data Index: 1143361 (The Pile)

Max Activating Token Index: 949

Text #11

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.6746. Min Act: -0.0000

Data Index: 304187 (The Pile)

Max Activating Token Index: 171

Text #12

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.6298. Min Act: -0.0000

Data Index: 115825 (The Pile)

Max Activating Token Index: 781

Text #13

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.5909. Min Act: -0.0000

Data Index: 1262571 (The Pile)

Max Activating Token Index: 794

Text #14

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.5374. Min Act: -0.0000

Data Index: 1921096 (The Pile)

Max Activating Token Index: 1009

Text #15

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.5834. Min Act: -0.0000

Data Index: 258770 (The Pile)

Max Activating Token Index: 381

Text #16

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.5274. Min Act: -0.0000

Data Index: 96592 (The Pile)

Max Activating Token Index: 900

Text #17

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.4934. Min Act: -0.0000

Data Index: 1513876 (The Pile)

Max Activating Token Index: 676

Text #18

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.4543. Min Act: -0.0000

Data Index: 217339 (The Pile)

Max Activating Token Index: 1001

Text #19

Max Range: 0.9527. Min Range: -0.9527

Max Act: 0.4328. Min Act: -0.0000

Data Index: 1020516 (The Pile)

Max Activating Token Index: 899