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

Dataset: The Pile

Neuron 1927 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.8630. Min Act: -0.0000

Data Index: 980982 (The Pile)

Max Activating Token Index: 415

Text #1

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.7518. Min Act: -0.0000

Data Index: 583496 (The Pile)

Max Activating Token Index: 919

Text #2

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.7263. Min Act: -0.0000

Data Index: 1913515 (The Pile)

Max Activating Token Index: 604

Text #3

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.6622. Min Act: -0.0000

Data Index: 1317242 (The Pile)

Max Activating Token Index: 419

Text #4

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.6408. Min Act: -0.0000

Data Index: 1792814 (The Pile)

Max Activating Token Index: 451

Text #5

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.6689. Min Act: -0.0000

Data Index: 1176512 (The Pile)

Max Activating Token Index: 578

Text #6

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.6412. Min Act: -0.0000

Data Index: 1070731 (The Pile)

Max Activating Token Index: 337

Text #7

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.6637. Min Act: -0.0000

Data Index: 330042 (The Pile)

Max Activating Token Index: 288

Text #8

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.6706. Min Act: -0.0000

Data Index: 712852 (The Pile)

Max Activating Token Index: 802

Text #9

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.6255. Min Act: -0.0000

Data Index: 448083 (The Pile)

Max Activating Token Index: 859

Text #10

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.6035. Min Act: -0.0000

Data Index: 276140 (The Pile)

Max Activating Token Index: 42

Text #11

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.6234. Min Act: -0.0000

Data Index: 669384 (The Pile)

Max Activating Token Index: 174

Text #12

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.6406. Min Act: -0.0000

Data Index: 963250 (The Pile)

Max Activating Token Index: 468

Text #13

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.6340. Min Act: -0.0000

Data Index: 210783 (The Pile)

Max Activating Token Index: 462

Text #14

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.5836. Min Act: -0.0000

Data Index: 429428 (The Pile)

Max Activating Token Index: 761

Text #15

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.5729. Min Act: -0.0000

Data Index: 391844 (The Pile)

Max Activating Token Index: 940

Text #16

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.6009. Min Act: -0.0000

Data Index: 975476 (The Pile)

Max Activating Token Index: 618

Text #17

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.5173. Min Act: -0.0000

Data Index: 1143179 (The Pile)

Max Activating Token Index: 887

Text #18

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.5761. Min Act: -0.0000

Data Index: 1302202 (The Pile)

Max Activating Token Index: 126

Text #19

Max Range: 0.8630. Min Range: -0.8630

Max Act: 0.5698. Min Act: -0.0000

Data Index: 1066960 (The Pile)

Max Activating Token Index: 660