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

Dataset: The Pile

Neuron 162 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2360. Min Range: -1.2360

Max Act: 1.2360. Min Act: 0.0000

Data Index: 433045 (The Pile)

Max Activating Token Index: 236

Text #1

Max Range: 1.2360. Min Range: -1.2360

Max Act: 1.1344. Min Act: -0.0000

Data Index: 22831 (The Pile)

Max Activating Token Index: 844

Text #2

Max Range: 1.2360. Min Range: -1.2360

Max Act: 1.1142. Min Act: -0.0000

Data Index: 878100 (The Pile)

Max Activating Token Index: 512

Text #3

Max Range: 1.2360. Min Range: -1.2360

Max Act: 0.9741. Min Act: -0.0000

Data Index: 1032305 (The Pile)

Max Activating Token Index: 604

Text #4

Max Range: 1.2360. Min Range: -1.2360

Max Act: 0.9297. Min Act: -0.0000

Data Index: 79850 (The Pile)

Max Activating Token Index: 402

Text #5

Max Range: 1.2360. Min Range: -1.2360

Max Act: 0.9920. Min Act: -0.0000

Data Index: 556909 (The Pile)

Max Activating Token Index: 48

Text #6

Max Range: 1.2360. Min Range: -1.2360

Max Act: 0.9657. Min Act: -0.0000

Data Index: 1814110 (The Pile)

Max Activating Token Index: 904

Text #7

Max Range: 1.2360. Min Range: -1.2360

Max Act: 0.8975. Min Act: 0.0000

Data Index: 1824244 (The Pile)

Max Activating Token Index: 518

Text #8

Max Range: 1.2360. Min Range: -1.2360

Max Act: 1.0161. Min Act: -0.0000

Data Index: 1028837 (The Pile)

Max Activating Token Index: 522

Text #9

Max Range: 1.2360. Min Range: -1.2360

Max Act: 0.9520. Min Act: -0.0000

Data Index: 144855 (The Pile)

Max Activating Token Index: 867

Text #10

Max Range: 1.2360. Min Range: -1.2360

Max Act: 0.9069. Min Act: -0.0000

Data Index: 241289 (The Pile)

Max Activating Token Index: 834

Text #11

Max Range: 1.2360. Min Range: -1.2360

Max Act: 0.9180. Min Act: -0.0000

Data Index: 1998401 (The Pile)

Max Activating Token Index: 918

Text #12

Max Range: 1.2360. Min Range: -1.2360

Max Act: 0.9127. Min Act: -0.0000

Data Index: 1088373 (The Pile)

Max Activating Token Index: 214

Text #13

Max Range: 1.2360. Min Range: -1.2360

Max Act: 0.9032. Min Act: -0.0000

Data Index: 637181 (The Pile)

Max Activating Token Index: 743

Text #14

Max Range: 1.2360. Min Range: -1.2360

Max Act: 0.9098. Min Act: -0.0000

Data Index: 1570769 (The Pile)

Max Activating Token Index: 661

Text #15

Max Range: 1.2360. Min Range: -1.2360

Max Act: 0.8829. Min Act: -0.0000

Data Index: 1565529 (The Pile)

Max Activating Token Index: 735

Text #16

Max Range: 1.2360. Min Range: -1.2360

Max Act: 0.8381. Min Act: -0.0000

Data Index: 1966071 (The Pile)

Max Activating Token Index: 528

Text #17

Max Range: 1.2360. Min Range: -1.2360

Max Act: 0.8397. Min Act: -0.0000

Data Index: 1333076 (The Pile)

Max Activating Token Index: 1020

Text #18

Max Range: 1.2360. Min Range: -1.2360

Max Act: 0.8298. Min Act: 0.0000

Data Index: 798097 (The Pile)

Max Activating Token Index: 983

Text #19

Max Range: 1.2360. Min Range: -1.2360

Max Act: 0.8324. Min Act: -0.0000

Data Index: 948430 (The Pile)

Max Activating Token Index: 701