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

Dataset: The Pile

Neuron 2106 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.5480. Min Act: -0.0000

Data Index: 539484 (The Pile)

Max Activating Token Index: 830

Text #1

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.5308. Min Act: -0.0000

Data Index: 432313 (The Pile)

Max Activating Token Index: 1020

Text #2

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.5207. Min Act: -0.0000

Data Index: 702126 (The Pile)

Max Activating Token Index: 418

Text #3

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.5259. Min Act: -0.0000

Data Index: 1620509 (The Pile)

Max Activating Token Index: 626

Text #4

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.4914. Min Act: -0.0000

Data Index: 1161511 (The Pile)

Max Activating Token Index: 804

Text #5

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.4249. Min Act: -0.0000

Data Index: 279084 (The Pile)

Max Activating Token Index: 928

Text #6

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.4602. Min Act: -0.0000

Data Index: 1854641 (The Pile)

Max Activating Token Index: 902

Text #7

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.4481. Min Act: -0.0000

Data Index: 241968 (The Pile)

Max Activating Token Index: 914

Text #8

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.4822. Min Act: -0.0000

Data Index: 1000273 (The Pile)

Max Activating Token Index: 35

Text #9

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.4459. Min Act: -0.0000

Data Index: 859735 (The Pile)

Max Activating Token Index: 60

Text #10

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.4303. Min Act: -0.0000

Data Index: 1389291 (The Pile)

Max Activating Token Index: 887

Text #11

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.4429. Min Act: -0.0000

Data Index: 1512011 (The Pile)

Max Activating Token Index: 266

Text #12

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.4343. Min Act: -0.0000

Data Index: 511124 (The Pile)

Max Activating Token Index: 473

Text #13

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.4075. Min Act: -0.0000

Data Index: 951430 (The Pile)

Max Activating Token Index: 1008

Text #14

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.4345. Min Act: -0.0000

Data Index: 1881822 (The Pile)

Max Activating Token Index: 1008

Text #15

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.4383. Min Act: -0.0000

Data Index: 1922342 (The Pile)

Max Activating Token Index: 967

Text #16

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.3934. Min Act: -0.0000

Data Index: 769444 (The Pile)

Max Activating Token Index: 253

Text #17

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.4283. Min Act: -0.0000

Data Index: 1885756 (The Pile)

Max Activating Token Index: 455

Text #18

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.4136. Min Act: -0.0000

Data Index: 1603252 (The Pile)

Max Activating Token Index: 1016

Text #19

Max Range: 0.5480. Min Range: -0.5480

Max Act: 0.4259. Min Act: -0.0000

Data Index: 611043 (The Pile)

Max Activating Token Index: 372