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

Dataset: The Pile

Neuron 4472 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: 0.2242. Min Range: -0.2242

Max Act: 0.2242. Min Act: -0.0000

Data Index: 1320286 (The Pile)

Max Activating Token Index: 68

Text #1

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1919. Min Act: -0.0000

Data Index: 911205 (The Pile)

Max Activating Token Index: 58

Text #2

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1773. Min Act: -0.0000

Data Index: 1179325 (The Pile)

Max Activating Token Index: 290

Text #3

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1620. Min Act: -0.0000

Data Index: 1447204 (The Pile)

Max Activating Token Index: 695

Text #4

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1842. Min Act: -0.0000

Data Index: 1574407 (The Pile)

Max Activating Token Index: 192

Text #5

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1927. Min Act: -0.0000

Data Index: 642301 (The Pile)

Max Activating Token Index: 619

Text #6

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1754. Min Act: -0.0000

Data Index: 680670 (The Pile)

Max Activating Token Index: 388

Text #7

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1743. Min Act: -0.0000

Data Index: 1184200 (The Pile)

Max Activating Token Index: 748

Text #8

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1787. Min Act: -0.0000

Data Index: 545789 (The Pile)

Max Activating Token Index: 430

Text #9

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1589. Min Act: -0.0000

Data Index: 428651 (The Pile)

Max Activating Token Index: 378

Text #10

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1738. Min Act: -0.0000

Data Index: 906824 (The Pile)

Max Activating Token Index: 574

Text #11

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1556. Min Act: -0.0000

Data Index: 46585 (The Pile)

Max Activating Token Index: 949

Text #12

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1713. Min Act: -0.0000

Data Index: 1992363 (The Pile)

Max Activating Token Index: 166

Text #13

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1578. Min Act: -0.0000

Data Index: 1465143 (The Pile)

Max Activating Token Index: 50

Text #14

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1299. Min Act: -0.0000

Data Index: 736703 (The Pile)

Max Activating Token Index: 675

Text #15

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1696. Min Act: -0.0000

Data Index: 1180424 (The Pile)

Max Activating Token Index: 43

Text #16

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1622. Min Act: -0.0000

Data Index: 302378 (The Pile)

Max Activating Token Index: 417

Text #17

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1590. Min Act: -0.0000

Data Index: 1490647 (The Pile)

Max Activating Token Index: 362

Text #18

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1449. Min Act: -0.0000

Data Index: 1098599 (The Pile)

Max Activating Token Index: 202

Text #19

Max Range: 0.2242. Min Range: -0.2242

Max Act: 0.1388. Min Act: -0.0000

Data Index: 717422 (The Pile)

Max Activating Token Index: 693