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

Dataset: The Pile

Neuron 3903 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: 0.0978. Min Range: -0.0978

Max Act: 0.0978. Min Act: -0.0000

Data Index: 1868115 (The Pile)

Max Activating Token Index: 165

Text #1

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0952. Min Act: -0.0000

Data Index: 1900554 (The Pile)

Max Activating Token Index: 421

Text #2

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0854. Min Act: -0.0000

Data Index: 1779871 (The Pile)

Max Activating Token Index: 394

Text #3

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0786. Min Act: -0.0000

Data Index: 1580288 (The Pile)

Max Activating Token Index: 935

Text #4

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0802. Min Act: -0.0000

Data Index: 476368 (The Pile)

Max Activating Token Index: 206

Text #5

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0759. Min Act: -0.0000

Data Index: 1443356 (The Pile)

Max Activating Token Index: 327

Text #6

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0773. Min Act: -0.0000

Data Index: 690861 (The Pile)

Max Activating Token Index: 607

Text #7

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0700. Min Act: -0.0000

Data Index: 1762697 (The Pile)

Max Activating Token Index: 273

Text #8

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0678. Min Act: -0.0000

Data Index: 787549 (The Pile)

Max Activating Token Index: 312

Text #9

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0682. Min Act: -0.0000

Data Index: 393637 (The Pile)

Max Activating Token Index: 964

Text #10

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0634. Min Act: -0.0000

Data Index: 1790352 (The Pile)

Max Activating Token Index: 494

Text #11

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0673. Min Act: -0.0000

Data Index: 697555 (The Pile)

Max Activating Token Index: 933

Text #12

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0696. Min Act: -0.0000

Data Index: 1728097 (The Pile)

Max Activating Token Index: 482

Text #13

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0636. Min Act: -0.0000

Data Index: 1376214 (The Pile)

Max Activating Token Index: 83

Text #14

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0608. Min Act: -0.0001

Data Index: 984001 (The Pile)

Max Activating Token Index: 500

Text #15

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0634. Min Act: -0.0000

Data Index: 1945184 (The Pile)

Max Activating Token Index: 1000

Text #16

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0530. Min Act: -0.0000

Data Index: 1027071 (The Pile)

Max Activating Token Index: 986

Text #17

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0605. Min Act: -0.0000

Data Index: 275118 (The Pile)

Max Activating Token Index: 431

Text #18

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0577. Min Act: -0.0000

Data Index: 602303 (The Pile)

Max Activating Token Index: 572

Text #19

Max Range: 0.0978. Min Range: -0.0978

Max Act: 0.0604. Min Act: -0.0000

Data Index: 1000263 (The Pile)

Max Activating Token Index: 614