Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3283 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4007. Min Range: -1.4007

Max Act: 1.4007. Min Act: -0.0000

Data Index: 436057 (The Pile)

Max Activating Token Index: 697

Text #1

Max Range: 1.4007. Min Range: -1.4007

Max Act: 1.1391. Min Act: -0.0000

Data Index: 1311327 (The Pile)

Max Activating Token Index: 759

Text #2

Max Range: 1.4007. Min Range: -1.4007

Max Act: 0.9935. Min Act: -0.0000

Data Index: 149999 (The Pile)

Max Activating Token Index: 983

Text #3

Max Range: 1.4007. Min Range: -1.4007

Max Act: 1.0882. Min Act: -0.0000

Data Index: 562127 (The Pile)

Max Activating Token Index: 582

Text #4

Max Range: 1.4007. Min Range: -1.4007

Max Act: 1.0411. Min Act: -0.0000

Data Index: 1333756 (The Pile)

Max Activating Token Index: 442

Text #5

Max Range: 1.4007. Min Range: -1.4007

Max Act: 0.9933. Min Act: -0.0000

Data Index: 1874018 (The Pile)

Max Activating Token Index: 624

Text #6

Max Range: 1.4007. Min Range: -1.4007

Max Act: 0.9649. Min Act: -0.0000

Data Index: 370324 (The Pile)

Max Activating Token Index: 1003

Text #7

Max Range: 1.4007. Min Range: -1.4007

Max Act: 0.9556. Min Act: -0.0000

Data Index: 478965 (The Pile)

Max Activating Token Index: 875

Text #8

Max Range: 1.4007. Min Range: -1.4007

Max Act: 1.0199. Min Act: -0.0000

Data Index: 635522 (The Pile)

Max Activating Token Index: 766

Text #9

Max Range: 1.4007. Min Range: -1.4007

Max Act: 0.7651. Min Act: -0.0000

Data Index: 241818 (The Pile)

Max Activating Token Index: 629

Text #10

Max Range: 1.4007. Min Range: -1.4007

Max Act: 1.0192. Min Act: -0.0000

Data Index: 1142319 (The Pile)

Max Activating Token Index: 1008

Text #11

Max Range: 1.4007. Min Range: -1.4007

Max Act: 0.8586. Min Act: -0.0000

Data Index: 1783422 (The Pile)

Max Activating Token Index: 776

Text #12

Max Range: 1.4007. Min Range: -1.4007

Max Act: 0.9189. Min Act: -0.0000

Data Index: 1094248 (The Pile)

Max Activating Token Index: 1011

Text #13

Max Range: 1.4007. Min Range: -1.4007

Max Act: 0.8789. Min Act: -0.0000

Data Index: 1348570 (The Pile)

Max Activating Token Index: 1015

Text #14

Max Range: 1.4007. Min Range: -1.4007

Max Act: 0.7992. Min Act: -0.0000

Data Index: 39529 (The Pile)

Max Activating Token Index: 801

Text #15

Max Range: 1.4007. Min Range: -1.4007

Max Act: 0.8457. Min Act: -0.0000

Data Index: 432995 (The Pile)

Max Activating Token Index: 623

Text #16

Max Range: 1.4007. Min Range: -1.4007

Max Act: 0.7974. Min Act: -0.0000

Data Index: 1261501 (The Pile)

Max Activating Token Index: 537

Text #17

Max Range: 1.4007. Min Range: -1.4007

Max Act: 0.7653. Min Act: -0.0000

Data Index: 1438005 (The Pile)

Max Activating Token Index: 421

Text #18

Max Range: 1.4007. Min Range: -1.4007

Max Act: 0.7970. Min Act: -0.0000

Data Index: 1459300 (The Pile)

Max Activating Token Index: 855

Text #19

Max Range: 1.4007. Min Range: -1.4007

Max Act: 0.8031. Min Act: -0.0000

Data Index: 1877523 (The Pile)

Max Activating Token Index: 902