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

Dataset: The Pile

Neuron 2300 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: 1.0222. Min Range: -1.0222

Max Act: 1.0222. Min Act: -0.0000

Data Index: 1508373 (The Pile)

Max Activating Token Index: 576

Text #1

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.7951. Min Act: -0.0000

Data Index: 361491 (The Pile)

Max Activating Token Index: 898

Text #2

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.8967. Min Act: -0.0000

Data Index: 1962489 (The Pile)

Max Activating Token Index: 504

Text #3

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.8837. Min Act: -0.0000

Data Index: 593980 (The Pile)

Max Activating Token Index: 702

Text #4

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.9075. Min Act: -0.0000

Data Index: 325348 (The Pile)

Max Activating Token Index: 968

Text #5

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.8928. Min Act: -0.0000

Data Index: 750306 (The Pile)

Max Activating Token Index: 1018

Text #6

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.8815. Min Act: -0.0000

Data Index: 1304581 (The Pile)

Max Activating Token Index: 675

Text #7

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.8654. Min Act: -0.0000

Data Index: 1597390 (The Pile)

Max Activating Token Index: 812

Text #8

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.8678. Min Act: -0.0000

Data Index: 1939554 (The Pile)

Max Activating Token Index: 299

Text #9

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.8618. Min Act: -0.0000

Data Index: 1912770 (The Pile)

Max Activating Token Index: 111

Text #10

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.8648. Min Act: -0.0000

Data Index: 1685218 (The Pile)

Max Activating Token Index: 393

Text #11

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.8718. Min Act: -0.0000

Data Index: 851578 (The Pile)

Max Activating Token Index: 628

Text #12

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.8866. Min Act: -0.0000

Data Index: 1604463 (The Pile)

Max Activating Token Index: 1014

Text #13

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.7360. Min Act: -0.0000

Data Index: 783265 (The Pile)

Max Activating Token Index: 1022

Text #14

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.8433. Min Act: -0.0000

Data Index: 438711 (The Pile)

Max Activating Token Index: 898

Text #15

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.8237. Min Act: -0.0000

Data Index: 896444 (The Pile)

Max Activating Token Index: 531

Text #16

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.8202. Min Act: -0.0000

Data Index: 1049532 (The Pile)

Max Activating Token Index: 153

Text #17

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.8634. Min Act: -0.0000

Data Index: 1810592 (The Pile)

Max Activating Token Index: 565

Text #18

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.7820. Min Act: -0.0000

Data Index: 226121 (The Pile)

Max Activating Token Index: 655

Text #19

Max Range: 1.0222. Min Range: -1.0222

Max Act: 0.8059. Min Act: -0.0000

Data Index: 1480070 (The Pile)

Max Activating Token Index: 553