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

Dataset: The Pile

Neuron 2003 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: 0.8752. Min Range: -0.8752

Max Act: 0.8752. Min Act: -0.0000

Data Index: 1218590 (The Pile)

Max Activating Token Index: 832

Text #1

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.8033. Min Act: -0.0000

Data Index: 1516501 (The Pile)

Max Activating Token Index: 135

Text #2

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.8102. Min Act: -0.0000

Data Index: 1450016 (The Pile)

Max Activating Token Index: 794

Text #3

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.8086. Min Act: -0.0000

Data Index: 204994 (The Pile)

Max Activating Token Index: 306

Text #4

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.7921. Min Act: -0.0000

Data Index: 321012 (The Pile)

Max Activating Token Index: 869

Text #5

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.6343. Min Act: -0.0000

Data Index: 1035441 (The Pile)

Max Activating Token Index: 518

Text #6

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.6838. Min Act: -0.0000

Data Index: 318817 (The Pile)

Max Activating Token Index: 166

Text #7

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.6986. Min Act: 0.0000

Data Index: 1629453 (The Pile)

Max Activating Token Index: 241

Text #8

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.6835. Min Act: -0.0000

Data Index: 582529 (The Pile)

Max Activating Token Index: 49

Text #9

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.5745. Min Act: -0.0000

Data Index: 961252 (The Pile)

Max Activating Token Index: 63

Text #10

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.5735. Min Act: -0.0000

Data Index: 1443325 (The Pile)

Max Activating Token Index: 36

Text #11

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.6534. Min Act: -0.0000

Data Index: 1151676 (The Pile)

Max Activating Token Index: 401

Text #12

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.5490. Min Act: -0.0000

Data Index: 1195591 (The Pile)

Max Activating Token Index: 220

Text #13

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.5520. Min Act: -0.0000

Data Index: 785725 (The Pile)

Max Activating Token Index: 22

Text #14

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.5420. Min Act: -0.0000

Data Index: 167873 (The Pile)

Max Activating Token Index: 779

Text #15

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.5486. Min Act: -0.0000

Data Index: 503765 (The Pile)

Max Activating Token Index: 381

Text #16

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.5256. Min Act: -0.0000

Data Index: 1252050 (The Pile)

Max Activating Token Index: 422

Text #17

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.4626. Min Act: -0.0000

Data Index: 2035 (The Pile)

Max Activating Token Index: 58

Text #18

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.5238. Min Act: -0.0000

Data Index: 232164 (The Pile)

Max Activating Token Index: 54

Text #19

Max Range: 0.8752. Min Range: -0.8752

Max Act: 0.5234. Min Act: -0.0000

Data Index: 1718846 (The Pile)

Max Activating Token Index: 262