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

Dataset: The Pile

Neuron 3001 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.8134. Min Act: -0.0000

Data Index: 1966599 (The Pile)

Max Activating Token Index: 898

Text #1

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.5902. Min Act: -0.0000

Data Index: 1664709 (The Pile)

Max Activating Token Index: 775

Text #2

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.5649. Min Act: -0.0000

Data Index: 1735276 (The Pile)

Max Activating Token Index: 912

Text #3

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.5778. Min Act: -0.0000

Data Index: 1046220 (The Pile)

Max Activating Token Index: 607

Text #4

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.5641. Min Act: 0.0000

Data Index: 546238 (The Pile)

Max Activating Token Index: 200

Text #5

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.5546. Min Act: -0.0000

Data Index: 1534742 (The Pile)

Max Activating Token Index: 167

Text #6

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.5585. Min Act: -0.0000

Data Index: 794258 (The Pile)

Max Activating Token Index: 112

Text #7

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.5886. Min Act: -0.0000

Data Index: 1453301 (The Pile)

Max Activating Token Index: 535

Text #8

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.5509. Min Act: -0.0000

Data Index: 969138 (The Pile)

Max Activating Token Index: 863

Text #9

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.5334. Min Act: 0.0000

Data Index: 1875041 (The Pile)

Max Activating Token Index: 257

Text #10

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.5122. Min Act: -0.0000

Data Index: 1896167 (The Pile)

Max Activating Token Index: 382

Text #11

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.5012. Min Act: 0.0000

Data Index: 859168 (The Pile)

Max Activating Token Index: 118

Text #12

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.5067. Min Act: -0.0000

Data Index: 1372529 (The Pile)

Max Activating Token Index: 465

Text #13

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.5031. Min Act: -0.0000

Data Index: 611186 (The Pile)

Max Activating Token Index: 1001

Text #14

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.4245. Min Act: -0.0000

Data Index: 355723 (The Pile)

Max Activating Token Index: 891

Text #15

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.4625. Min Act: -0.0000

Data Index: 309438 (The Pile)

Max Activating Token Index: 720

Text #16

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.4746. Min Act: -0.0000

Data Index: 105754 (The Pile)

Max Activating Token Index: 358

Text #17

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.4779. Min Act: -0.0000

Data Index: 426320 (The Pile)

Max Activating Token Index: 131

Text #18

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.4191. Min Act: -0.0000

Data Index: 74928 (The Pile)

Max Activating Token Index: 687

Text #19

Max Range: 0.8134. Min Range: -0.8134

Max Act: 0.4449. Min Act: -0.0000

Data Index: 1583644 (The Pile)

Max Activating Token Index: 803