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

Dataset: The Pile

Neuron 1578 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4458. Min Range: -4.4458

Max Act: 4.4458. Min Act: -0.0000

Data Index: 28796 (The Pile)

Max Activating Token Index: 580

Text #1

Max Range: 4.4458. Min Range: -4.4458

Max Act: 3.9654. Min Act: -0.0000

Data Index: 1441946 (The Pile)

Max Activating Token Index: 456

Text #2

Max Range: 4.4458. Min Range: -4.4458

Max Act: 3.6822. Min Act: -0.0000

Data Index: 966328 (The Pile)

Max Activating Token Index: 953

Text #3

Max Range: 4.4458. Min Range: -4.4458

Max Act: 3.7659. Min Act: -0.0000

Data Index: 841251 (The Pile)

Max Activating Token Index: 712

Text #4

Max Range: 4.4458. Min Range: -4.4458

Max Act: 3.6327. Min Act: -0.0000

Data Index: 620067 (The Pile)

Max Activating Token Index: 894

Text #5

Max Range: 4.4458. Min Range: -4.4458

Max Act: 3.4877. Min Act: -0.0000

Data Index: 1053646 (The Pile)

Max Activating Token Index: 786

Text #6

Max Range: 4.4458. Min Range: -4.4458

Max Act: 3.4357. Min Act: -0.0000

Data Index: 723188 (The Pile)

Max Activating Token Index: 691

Text #7

Max Range: 4.4458. Min Range: -4.4458

Max Act: 3.3204. Min Act: -0.0000

Data Index: 1053365 (The Pile)

Max Activating Token Index: 943

Text #8

Max Range: 4.4458. Min Range: -4.4458

Max Act: 3.4856. Min Act: -0.0000

Data Index: 1545680 (The Pile)

Max Activating Token Index: 475

Text #9

Max Range: 4.4458. Min Range: -4.4458

Max Act: 3.3122. Min Act: -0.0000

Data Index: 1392897 (The Pile)

Max Activating Token Index: 476

Text #10

Max Range: 4.4458. Min Range: -4.4458

Max Act: 3.4062. Min Act: -0.0000

Data Index: 1744359 (The Pile)

Max Activating Token Index: 691

Text #11

Max Range: 4.4458. Min Range: -4.4458

Max Act: 3.3664. Min Act: -0.0000

Data Index: 1248479 (The Pile)

Max Activating Token Index: 411

Text #12

Max Range: 4.4458. Min Range: -4.4458

Max Act: 3.3536. Min Act: -0.0000

Data Index: 1220769 (The Pile)

Max Activating Token Index: 976

Text #13

Max Range: 4.4458. Min Range: -4.4458

Max Act: 3.4868. Min Act: -0.0000

Data Index: 1820643 (The Pile)

Max Activating Token Index: 872

Text #14

Max Range: 4.4458. Min Range: -4.4458

Max Act: 3.1796. Min Act: -0.0000

Data Index: 914857 (The Pile)

Max Activating Token Index: 24

Text #15

Max Range: 4.4458. Min Range: -4.4458

Max Act: 3.2192. Min Act: -0.0000

Data Index: 952399 (The Pile)

Max Activating Token Index: 817

Text #16

Max Range: 4.4458. Min Range: -4.4458

Max Act: 3.4087. Min Act: -0.0000

Data Index: 1865760 (The Pile)

Max Activating Token Index: 887

Text #17

Max Range: 4.4458. Min Range: -4.4458

Max Act: 3.1526. Min Act: -0.0000

Data Index: 1856234 (The Pile)

Max Activating Token Index: 456

Text #18

Max Range: 4.4458. Min Range: -4.4458

Max Act: 2.7043. Min Act: -0.0000

Data Index: 1302784 (The Pile)

Max Activating Token Index: 834

Text #19

Max Range: 4.4458. Min Range: -4.4458

Max Act: 3.2889. Min Act: -0.0000

Data Index: 716860 (The Pile)

Max Activating Token Index: 987