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

Dataset: The Pile

Neuron 1496 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: 3.8896. Min Range: -3.8896

Max Act: 3.6063. Min Act: -0.0000

Data Index: 125679 (The Pile)

Max Activating Token Index: 167

Text #1

Max Range: 3.8896. Min Range: -3.8896

Max Act: 3.8896. Min Act: -0.0000

Data Index: 1028354 (The Pile)

Max Activating Token Index: 847

Text #2

Max Range: 3.8896. Min Range: -3.8896

Max Act: 3.3886. Min Act: -0.0000

Data Index: 688462 (The Pile)

Max Activating Token Index: 121

Text #3

Max Range: 3.8896. Min Range: -3.8896

Max Act: 3.0913. Min Act: -0.0000

Data Index: 1042655 (The Pile)

Max Activating Token Index: 1001

Text #4

Max Range: 3.8896. Min Range: -3.8896

Max Act: 3.5022. Min Act: -0.0000

Data Index: 1296057 (The Pile)

Max Activating Token Index: 89

Text #5

Max Range: 3.8896. Min Range: -3.8896

Max Act: 3.2910. Min Act: -0.0000

Data Index: 1501860 (The Pile)

Max Activating Token Index: 701

Text #6

Max Range: 3.8896. Min Range: -3.8896

Max Act: 3.3156. Min Act: -0.0000

Data Index: 1300592 (The Pile)

Max Activating Token Index: 753

Text #7

Max Range: 3.8896. Min Range: -3.8896

Max Act: 3.0566. Min Act: -0.0000

Data Index: 12034 (The Pile)

Max Activating Token Index: 748

Text #8

Max Range: 3.8896. Min Range: -3.8896

Max Act: 2.9211. Min Act: -0.0000

Data Index: 1189921 (The Pile)

Max Activating Token Index: 661

Text #9

Max Range: 3.8896. Min Range: -3.8896

Max Act: 2.9884. Min Act: -0.0000

Data Index: 1093284 (The Pile)

Max Activating Token Index: 524

Text #10

Max Range: 3.8896. Min Range: -3.8896

Max Act: 3.1430. Min Act: -0.0000

Data Index: 1938121 (The Pile)

Max Activating Token Index: 781

Text #11

Max Range: 3.8896. Min Range: -3.8896

Max Act: 3.6130. Min Act: -0.0000

Data Index: 75607 (The Pile)

Max Activating Token Index: 655

Text #12

Max Range: 3.8896. Min Range: -3.8896

Max Act: 3.0975. Min Act: -0.0000

Data Index: 1418545 (The Pile)

Max Activating Token Index: 143

Text #13

Max Range: 3.8896. Min Range: -3.8896

Max Act: 2.9610. Min Act: -0.0000

Data Index: 1779040 (The Pile)

Max Activating Token Index: 478

Text #14

Max Range: 3.8896. Min Range: -3.8896

Max Act: 3.2629. Min Act: -0.0000

Data Index: 1872024 (The Pile)

Max Activating Token Index: 401

Text #15

Max Range: 3.8896. Min Range: -3.8896

Max Act: 3.2245. Min Act: -0.0000

Data Index: 1599948 (The Pile)

Max Activating Token Index: 556

Text #16

Max Range: 3.8896. Min Range: -3.8896

Max Act: 3.0255. Min Act: -0.0000

Data Index: 1267067 (The Pile)

Max Activating Token Index: 510

Text #17

Max Range: 3.8896. Min Range: -3.8896

Max Act: 3.1303. Min Act: -0.0000

Data Index: 1334678 (The Pile)

Max Activating Token Index: 818

Text #18

Max Range: 3.8896. Min Range: -3.8896

Max Act: 3.0983. Min Act: -0.0000

Data Index: 565609 (The Pile)

Max Activating Token Index: 554

Text #19

Max Range: 3.8896. Min Range: -3.8896

Max Act: 2.9628. Min Act: -0.0000

Data Index: 478618 (The Pile)

Max Activating Token Index: 443