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

Dataset: The Pile

Neuron 4614 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: 0.2585. Min Range: -0.2585

Max Act: 0.2585. Min Act: -0.0000

Data Index: 392360 (The Pile)

Max Activating Token Index: 273

Text #1

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2543. Min Act: -0.0000

Data Index: 1484821 (The Pile)

Max Activating Token Index: 456

Text #2

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2014. Min Act: -0.0000

Data Index: 662178 (The Pile)

Max Activating Token Index: 466

Text #3

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1516. Min Act: -0.0000

Data Index: 775149 (The Pile)

Max Activating Token Index: 947

Text #4

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1822. Min Act: -0.0000

Data Index: 629548 (The Pile)

Max Activating Token Index: 978

Text #5

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1794. Min Act: -0.0000

Data Index: 1171311 (The Pile)

Max Activating Token Index: 396

Text #6

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1508. Min Act: -0.0000

Data Index: 1221446 (The Pile)

Max Activating Token Index: 586

Text #7

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1433. Min Act: -0.0000

Data Index: 1085662 (The Pile)

Max Activating Token Index: 887

Text #8

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1578. Min Act: -0.0000

Data Index: 1800768 (The Pile)

Max Activating Token Index: 661

Text #9

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1429. Min Act: -0.0000

Data Index: 1267390 (The Pile)

Max Activating Token Index: 875

Text #10

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1539. Min Act: -0.0000

Data Index: 1684776 (The Pile)

Max Activating Token Index: 979

Text #11

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1532. Min Act: -0.0000

Data Index: 1976067 (The Pile)

Max Activating Token Index: 680

Text #12

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1891. Min Act: -0.0000

Data Index: 1360962 (The Pile)

Max Activating Token Index: 834

Text #13

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1739. Min Act: -0.0000

Data Index: 1780267 (The Pile)

Max Activating Token Index: 903

Text #14

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1424. Min Act: -0.0000

Data Index: 1535783 (The Pile)

Max Activating Token Index: 914

Text #15

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1483. Min Act: -0.0000

Data Index: 1218491 (The Pile)

Max Activating Token Index: 850

Text #16

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1567. Min Act: -0.0000

Data Index: 964209 (The Pile)

Max Activating Token Index: 851

Text #17

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1308. Min Act: -0.0000

Data Index: 1531951 (The Pile)

Max Activating Token Index: 1009

Text #18

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1400. Min Act: -0.0000

Data Index: 1915543 (The Pile)

Max Activating Token Index: 995

Text #19

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1411. Min Act: -0.0000

Data Index: 1241393 (The Pile)

Max Activating Token Index: 660