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

Dataset: The Pile

Neuron 2168 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: 3.4773. Min Range: -3.4773

Max Act: 3.3146. Min Act: -0.0000

Data Index: 1011658 (The Pile)

Max Activating Token Index: 945

Text #1

Max Range: 3.4773. Min Range: -3.4773

Max Act: 3.4773. Min Act: -0.0000

Data Index: 1140183 (The Pile)

Max Activating Token Index: 984

Text #2

Max Range: 3.4773. Min Range: -3.4773

Max Act: 3.0368. Min Act: -0.0000

Data Index: 949691 (The Pile)

Max Activating Token Index: 1016

Text #3

Max Range: 3.4773. Min Range: -3.4773

Max Act: 3.1775. Min Act: -0.0000

Data Index: 1707282 (The Pile)

Max Activating Token Index: 713

Text #4

Max Range: 3.4773. Min Range: -3.4773

Max Act: 3.0961. Min Act: -0.0000

Data Index: 1183093 (The Pile)

Max Activating Token Index: 976

Text #5

Max Range: 3.4773. Min Range: -3.4773

Max Act: 3.2121. Min Act: -0.0000

Data Index: 269322 (The Pile)

Max Activating Token Index: 354

Text #6

Max Range: 3.4773. Min Range: -3.4773

Max Act: 3.2326. Min Act: -0.0000

Data Index: 274151 (The Pile)

Max Activating Token Index: 993

Text #7

Max Range: 3.4773. Min Range: -3.4773

Max Act: 3.2896. Min Act: -0.0000

Data Index: 1696847 (The Pile)

Max Activating Token Index: 430

Text #8

Max Range: 3.4773. Min Range: -3.4773

Max Act: 3.1429. Min Act: -0.0000

Data Index: 1912875 (The Pile)

Max Activating Token Index: 212

Text #9

Max Range: 3.4773. Min Range: -3.4773

Max Act: 3.4697. Min Act: -0.0000

Data Index: 1355907 (The Pile)

Max Activating Token Index: 937

Text #10

Max Range: 3.4773. Min Range: -3.4773

Max Act: 3.1357. Min Act: -0.0000

Data Index: 643786 (The Pile)

Max Activating Token Index: 815

Text #11

Max Range: 3.4773. Min Range: -3.4773

Max Act: 2.8916. Min Act: -0.0000

Data Index: 474440 (The Pile)

Max Activating Token Index: 667

Text #12

Max Range: 3.4773. Min Range: -3.4773

Max Act: 3.0834. Min Act: -0.0000

Data Index: 377866 (The Pile)

Max Activating Token Index: 545

Text #13

Max Range: 3.4773. Min Range: -3.4773

Max Act: 2.9874. Min Act: -0.0000

Data Index: 1579635 (The Pile)

Max Activating Token Index: 924

Text #14

Max Range: 3.4773. Min Range: -3.4773

Max Act: 2.7753. Min Act: -0.0000

Data Index: 1261457 (The Pile)

Max Activating Token Index: 912

Text #15

Max Range: 3.4773. Min Range: -3.4773

Max Act: 3.0727. Min Act: -0.0000

Data Index: 949094 (The Pile)

Max Activating Token Index: 356

Text #16

Max Range: 3.4773. Min Range: -3.4773

Max Act: 2.8347. Min Act: -0.0000

Data Index: 171652 (The Pile)

Max Activating Token Index: 1018

Text #17

Max Range: 3.4773. Min Range: -3.4773

Max Act: 2.9356. Min Act: -0.0000

Data Index: 883043 (The Pile)

Max Activating Token Index: 781

Text #18

Max Range: 3.4773. Min Range: -3.4773

Max Act: 2.8420. Min Act: -0.0000

Data Index: 1942727 (The Pile)

Max Activating Token Index: 959

Text #19

Max Range: 3.4773. Min Range: -3.4773

Max Act: 2.5608. Min Act: -0.0000

Data Index: 359593 (The Pile)

Max Activating Token Index: 850