Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3795 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 4.1719. Min Range: -4.1719

Max Act: 4.1719. Min Act: -0.0000

Data Index: 898891 (The Pile)

Max Activating Token Index: 781

Text #1

Max Range: 4.1719. Min Range: -4.1719

Max Act: 3.7741. Min Act: -0.0000

Data Index: 1228328 (The Pile)

Max Activating Token Index: 246

Text #2

Max Range: 4.1719. Min Range: -4.1719

Max Act: 3.8724. Min Act: -0.0000

Data Index: 1231548 (The Pile)

Max Activating Token Index: 330

Text #3

Max Range: 4.1719. Min Range: -4.1719

Max Act: 3.8212. Min Act: -0.0000

Data Index: 605511 (The Pile)

Max Activating Token Index: 640

Text #4

Max Range: 4.1719. Min Range: -4.1719

Max Act: 3.7666. Min Act: -0.0000

Data Index: 177279 (The Pile)

Max Activating Token Index: 948

Text #5

Max Range: 4.1719. Min Range: -4.1719

Max Act: 4.1223. Min Act: -0.0000

Data Index: 1973766 (The Pile)

Max Activating Token Index: 187

Text #6

Max Range: 4.1719. Min Range: -4.1719

Max Act: 3.6937. Min Act: -0.0000

Data Index: 570718 (The Pile)

Max Activating Token Index: 610

Text #7

Max Range: 4.1719. Min Range: -4.1719

Max Act: 3.6354. Min Act: -0.0000

Data Index: 1646917 (The Pile)

Max Activating Token Index: 470

Text #8

Max Range: 4.1719. Min Range: -4.1719

Max Act: 3.5853. Min Act: -0.0000

Data Index: 1010828 (The Pile)

Max Activating Token Index: 309

Text #9

Max Range: 4.1719. Min Range: -4.1719

Max Act: 3.3495. Min Act: -0.0000

Data Index: 1093089 (The Pile)

Max Activating Token Index: 757

Text #10

Max Range: 4.1719. Min Range: -4.1719

Max Act: 3.2981. Min Act: -0.0000

Data Index: 604300 (The Pile)

Max Activating Token Index: 457

Text #11

Max Range: 4.1719. Min Range: -4.1719

Max Act: 3.5539. Min Act: -0.0000

Data Index: 864593 (The Pile)

Max Activating Token Index: 246

Text #12

Max Range: 4.1719. Min Range: -4.1719

Max Act: 2.8804. Min Act: -0.0000

Data Index: 1300188 (The Pile)

Max Activating Token Index: 433

Text #13

Max Range: 4.1719. Min Range: -4.1719

Max Act: 3.6395. Min Act: -0.0000

Data Index: 749787 (The Pile)

Max Activating Token Index: 239

Text #14

Max Range: 4.1719. Min Range: -4.1719

Max Act: 3.3183. Min Act: -0.0000

Data Index: 950008 (The Pile)

Max Activating Token Index: 627

Text #15

Max Range: 4.1719. Min Range: -4.1719

Max Act: 3.1132. Min Act: -0.0000

Data Index: 471711 (The Pile)

Max Activating Token Index: 386

Text #16

Max Range: 4.1719. Min Range: -4.1719

Max Act: 3.0660. Min Act: -0.0000

Data Index: 1107225 (The Pile)

Max Activating Token Index: 248

Text #17

Max Range: 4.1719. Min Range: -4.1719

Max Act: 3.1752. Min Act: -0.0000

Data Index: 1141375 (The Pile)

Max Activating Token Index: 864

Text #18

Max Range: 4.1719. Min Range: -4.1719

Max Act: 3.1694. Min Act: -0.0000

Data Index: 112281 (The Pile)

Max Activating Token Index: 878

Text #19

Max Range: 4.1719. Min Range: -4.1719

Max Act: 2.9185. Min Act: -0.0000

Data Index: 209892 (The Pile)

Max Activating Token Index: 321