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

Dataset: The Pile

Neuron 4664 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0855. Min Range: -1.0855

Max Act: 1.0855. Min Act: -0.0000

Data Index: 1122851 (The Pile)

Max Activating Token Index: 621

Text #1

Max Range: 1.0855. Min Range: -1.0855

Max Act: 1.0052. Min Act: -0.0000

Data Index: 473974 (The Pile)

Max Activating Token Index: 389

Text #2

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.9132. Min Act: -0.0000

Data Index: 174450 (The Pile)

Max Activating Token Index: 960

Text #3

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.9734. Min Act: -0.0000

Data Index: 1609842 (The Pile)

Max Activating Token Index: 110

Text #4

Max Range: 1.0855. Min Range: -1.0855

Max Act: 1.0365. Min Act: -0.0000

Data Index: 1465640 (The Pile)

Max Activating Token Index: 473

Text #5

Max Range: 1.0855. Min Range: -1.0855

Max Act: 1.0329. Min Act: -0.0000

Data Index: 247141 (The Pile)

Max Activating Token Index: 973

Text #6

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.9438. Min Act: -0.0000

Data Index: 215043 (The Pile)

Max Activating Token Index: 691

Text #7

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.9318. Min Act: -0.0000

Data Index: 1853315 (The Pile)

Max Activating Token Index: 878

Text #8

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.9180. Min Act: -0.0000

Data Index: 955481 (The Pile)

Max Activating Token Index: 149

Text #9

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.8606. Min Act: -0.0000

Data Index: 992868 (The Pile)

Max Activating Token Index: 821

Text #10

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.9151. Min Act: -0.0000

Data Index: 1166567 (The Pile)

Max Activating Token Index: 87

Text #11

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.9587. Min Act: -0.0000

Data Index: 1373439 (The Pile)

Max Activating Token Index: 621

Text #12

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.9253. Min Act: -0.0000

Data Index: 1802568 (The Pile)

Max Activating Token Index: 606

Text #13

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.8229. Min Act: -0.0000

Data Index: 257385 (The Pile)

Max Activating Token Index: 362

Text #14

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.8242. Min Act: -0.0000

Data Index: 820016 (The Pile)

Max Activating Token Index: 480

Text #15

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.8674. Min Act: -0.0000

Data Index: 521033 (The Pile)

Max Activating Token Index: 50

Text #16

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.8564. Min Act: -0.0000

Data Index: 1911032 (The Pile)

Max Activating Token Index: 448

Text #17

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.9111. Min Act: -0.0000

Data Index: 915728 (The Pile)

Max Activating Token Index: 781

Text #18

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.8093. Min Act: 0.0001

Data Index: 1412415 (The Pile)

Max Activating Token Index: 569

Text #19

Max Range: 1.0855. Min Range: -1.0855

Max Act: 0.7985. Min Act: -0.0000

Data Index: 1934680 (The Pile)

Max Activating Token Index: 337