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

Dataset: The Pile

Neuron 654 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: 0.6006. Min Range: -0.6006

Max Act: 0.5746. Min Act: -0.0000

Data Index: 397795 (The Pile)

Max Activating Token Index: 716

Text #1

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5712. Min Act: -0.0000

Data Index: 162880 (The Pile)

Max Activating Token Index: 969

Text #2

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5043. Min Act: -0.0000

Data Index: 219832 (The Pile)

Max Activating Token Index: 930

Text #3

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.6006. Min Act: -0.0000

Data Index: 1295869 (The Pile)

Max Activating Token Index: 687

Text #4

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5453. Min Act: -0.0000

Data Index: 253103 (The Pile)

Max Activating Token Index: 35

Text #5

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5507. Min Act: -0.0000

Data Index: 931819 (The Pile)

Max Activating Token Index: 665

Text #6

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5592. Min Act: -0.0000

Data Index: 267305 (The Pile)

Max Activating Token Index: 793

Text #7

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5506. Min Act: -0.0000

Data Index: 545323 (The Pile)

Max Activating Token Index: 970

Text #8

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4933. Min Act: -0.0000

Data Index: 949472 (The Pile)

Max Activating Token Index: 662

Text #9

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4946. Min Act: -0.0000

Data Index: 607414 (The Pile)

Max Activating Token Index: 556

Text #10

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5223. Min Act: -0.0000

Data Index: 1740992 (The Pile)

Max Activating Token Index: 417

Text #11

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4830. Min Act: -0.0000

Data Index: 763288 (The Pile)

Max Activating Token Index: 324

Text #12

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5212. Min Act: -0.0000

Data Index: 882311 (The Pile)

Max Activating Token Index: 695

Text #13

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4830. Min Act: -0.0000

Data Index: 1300566 (The Pile)

Max Activating Token Index: 620

Text #14

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4691. Min Act: -0.0000

Data Index: 1294037 (The Pile)

Max Activating Token Index: 150

Text #15

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4709. Min Act: -0.0000

Data Index: 598612 (The Pile)

Max Activating Token Index: 689

Text #16

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5046. Min Act: -0.0000

Data Index: 504541 (The Pile)

Max Activating Token Index: 345

Text #17

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4822. Min Act: -0.0000

Data Index: 257880 (The Pile)

Max Activating Token Index: 462

Text #18

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.4533. Min Act: -0.0000

Data Index: 1792982 (The Pile)

Max Activating Token Index: 814

Text #19

Max Range: 0.6006. Min Range: -0.6006

Max Act: 0.5097. Min Act: -0.0000

Data Index: 1860605 (The Pile)

Max Activating Token Index: 233