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

Dataset: The Pile

Neuron 2648 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: 0.9996. Min Range: -0.9996

Max Act: 0.9996. Min Act: -0.0000

Data Index: 1982345 (The Pile)

Max Activating Token Index: 750

Text #1

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.9892. Min Act: -0.0000

Data Index: 276927 (The Pile)

Max Activating Token Index: 469

Text #2

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.8165. Min Act: -0.0000

Data Index: 875981 (The Pile)

Max Activating Token Index: 272

Text #3

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.8150. Min Act: -0.0000

Data Index: 526536 (The Pile)

Max Activating Token Index: 782

Text #4

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7786. Min Act: -0.0000

Data Index: 502980 (The Pile)

Max Activating Token Index: 732

Text #5

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7225. Min Act: -0.0000

Data Index: 198962 (The Pile)

Max Activating Token Index: 70

Text #6

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7401. Min Act: -0.0000

Data Index: 1105102 (The Pile)

Max Activating Token Index: 675

Text #7

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7726. Min Act: -0.0000

Data Index: 1554724 (The Pile)

Max Activating Token Index: 237

Text #8

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7445. Min Act: -0.0000

Data Index: 1909712 (The Pile)

Max Activating Token Index: 295

Text #9

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7132. Min Act: -0.0000

Data Index: 577180 (The Pile)

Max Activating Token Index: 620

Text #10

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7310. Min Act: -0.0000

Data Index: 472739 (The Pile)

Max Activating Token Index: 857

Text #11

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7098. Min Act: -0.0000

Data Index: 1181779 (The Pile)

Max Activating Token Index: 848

Text #12

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7306. Min Act: -0.0000

Data Index: 1919816 (The Pile)

Max Activating Token Index: 115

Text #13

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.7084. Min Act: -0.0000

Data Index: 1952955 (The Pile)

Max Activating Token Index: 650

Text #14

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.6708. Min Act: -0.0000

Data Index: 340009 (The Pile)

Max Activating Token Index: 139

Text #15

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.6914. Min Act: -0.0000

Data Index: 283311 (The Pile)

Max Activating Token Index: 611

Text #16

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.6359. Min Act: -0.0000

Data Index: 1345230 (The Pile)

Max Activating Token Index: 710

Text #17

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.6716. Min Act: -0.0000

Data Index: 1025526 (The Pile)

Max Activating Token Index: 501

Text #18

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.6268. Min Act: -0.0000

Data Index: 1008098 (The Pile)

Max Activating Token Index: 462

Text #19

Max Range: 0.9996. Min Range: -0.9996

Max Act: 0.6440. Min Act: -0.0000

Data Index: 1093876 (The Pile)

Max Activating Token Index: 1002