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

Dataset: The Pile

Neuron 2927 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: 5.4494. Min Range: -5.4494

Max Act: 5.4494. Min Act: -0.0000

Data Index: 1204923 (The Pile)

Max Activating Token Index: 327

Text #1

Max Range: 5.4494. Min Range: -5.4494

Max Act: 4.4926. Min Act: -0.0000

Data Index: 865875 (The Pile)

Max Activating Token Index: 92

Text #2

Max Range: 5.4494. Min Range: -5.4494

Max Act: 4.1468. Min Act: -0.0000

Data Index: 741831 (The Pile)

Max Activating Token Index: 640

Text #3

Max Range: 5.4494. Min Range: -5.4494

Max Act: 4.1189. Min Act: -0.0000

Data Index: 1310757 (The Pile)

Max Activating Token Index: 1015

Text #4

Max Range: 5.4494. Min Range: -5.4494

Max Act: 4.9442. Min Act: -0.0000

Data Index: 798365 (The Pile)

Max Activating Token Index: 825

Text #5

Max Range: 5.4494. Min Range: -5.4494

Max Act: 4.9518. Min Act: -0.0000

Data Index: 730230 (The Pile)

Max Activating Token Index: 704

Text #6

Max Range: 5.4494. Min Range: -5.4494

Max Act: 3.2840. Min Act: -0.0000

Data Index: 1397935 (The Pile)

Max Activating Token Index: 683

Text #7

Max Range: 5.4494. Min Range: -5.4494

Max Act: 4.4104. Min Act: -0.0000

Data Index: 844391 (The Pile)

Max Activating Token Index: 926

Text #8

Max Range: 5.4494. Min Range: -5.4494

Max Act: 4.3702. Min Act: -0.0000

Data Index: 393029 (The Pile)

Max Activating Token Index: 782

Text #9

Max Range: 5.4494. Min Range: -5.4494

Max Act: 4.1725. Min Act: -0.0000

Data Index: 1902787 (The Pile)

Max Activating Token Index: 548

Text #10

Max Range: 5.4494. Min Range: -5.4494

Max Act: 3.8524. Min Act: -0.0000

Data Index: 228152 (The Pile)

Max Activating Token Index: 122

Text #11

Max Range: 5.4494. Min Range: -5.4494

Max Act: 4.0436. Min Act: -0.0000

Data Index: 1342605 (The Pile)

Max Activating Token Index: 309

Text #12

Max Range: 5.4494. Min Range: -5.4494

Max Act: 3.8707. Min Act: -0.0000

Data Index: 235133 (The Pile)

Max Activating Token Index: 930

Text #13

Max Range: 5.4494. Min Range: -5.4494

Max Act: 2.9719. Min Act: -0.0000

Data Index: 1018418 (The Pile)

Max Activating Token Index: 105

Text #14

Max Range: 5.4494. Min Range: -5.4494

Max Act: 3.5578. Min Act: -0.0000

Data Index: 1209702 (The Pile)

Max Activating Token Index: 320

Text #15

Max Range: 5.4494. Min Range: -5.4494

Max Act: 3.7027. Min Act: -0.0000

Data Index: 1818263 (The Pile)

Max Activating Token Index: 578

Text #16

Max Range: 5.4494. Min Range: -5.4494

Max Act: 3.5131. Min Act: -0.0000

Data Index: 1302756 (The Pile)

Max Activating Token Index: 909

Text #17

Max Range: 5.4494. Min Range: -5.4494

Max Act: 3.8489. Min Act: -0.0000

Data Index: 876970 (The Pile)

Max Activating Token Index: 759

Text #18

Max Range: 5.4494. Min Range: -5.4494

Max Act: 3.4933. Min Act: -0.0000

Data Index: 1811661 (The Pile)

Max Activating Token Index: 204

Text #19

Max Range: 5.4494. Min Range: -5.4494

Max Act: 3.7620. Min Act: -0.0000

Data Index: 505336 (The Pile)

Max Activating Token Index: 274