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

Dataset: The Pile

Neuron 4446 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: 0.6249. Min Range: -0.6249

Max Act: 0.5975. Min Act: -0.0000

Data Index: 1767474 (The Pile)

Max Activating Token Index: 31

Text #1

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.6249. Min Act: -0.0000

Data Index: 1296408 (The Pile)

Max Activating Token Index: 1006

Text #2

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5772. Min Act: -0.0000

Data Index: 1681316 (The Pile)

Max Activating Token Index: 47

Text #3

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.6180. Min Act: -0.0000

Data Index: 392412 (The Pile)

Max Activating Token Index: 19

Text #4

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5964. Min Act: -0.0000

Data Index: 509998 (The Pile)

Max Activating Token Index: 107

Text #5

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5737. Min Act: -0.0000

Data Index: 1074389 (The Pile)

Max Activating Token Index: 1003

Text #6

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5472. Min Act: -0.0000

Data Index: 1312102 (The Pile)

Max Activating Token Index: 22

Text #7

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5280. Min Act: -0.0000

Data Index: 40443 (The Pile)

Max Activating Token Index: 20

Text #8

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5442. Min Act: -0.0000

Data Index: 1789373 (The Pile)

Max Activating Token Index: 310

Text #9

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5751. Min Act: -0.0000

Data Index: 1958743 (The Pile)

Max Activating Token Index: 1003

Text #10

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5701. Min Act: -0.0000

Data Index: 190158 (The Pile)

Max Activating Token Index: 677

Text #11

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5454. Min Act: -0.0000

Data Index: 496605 (The Pile)

Max Activating Token Index: 893

Text #12

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5475. Min Act: -0.0000

Data Index: 1403158 (The Pile)

Max Activating Token Index: 435

Text #13

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5128. Min Act: -0.0000

Data Index: 330992 (The Pile)

Max Activating Token Index: 57

Text #14

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5269. Min Act: -0.0000

Data Index: 1733866 (The Pile)

Max Activating Token Index: 501

Text #15

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5496. Min Act: -0.0000

Data Index: 186457 (The Pile)

Max Activating Token Index: 23

Text #16

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5789. Min Act: -0.0000

Data Index: 30188 (The Pile)

Max Activating Token Index: 964

Text #17

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5063. Min Act: -0.0000

Data Index: 900707 (The Pile)

Max Activating Token Index: 260

Text #18

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.5014. Min Act: -0.0000

Data Index: 288290 (The Pile)

Max Activating Token Index: 856

Text #19

Max Range: 0.6249. Min Range: -0.6249

Max Act: 0.4792. Min Act: 0.0000

Data Index: 13998 (The Pile)

Max Activating Token Index: 968