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

Dataset: The Pile

Neuron 2376 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.6467. Min Act: -0.0000

Data Index: 520783 (The Pile)

Max Activating Token Index: 279

Text #1

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.5833. Min Act: -0.0000

Data Index: 1666751 (The Pile)

Max Activating Token Index: 33

Text #2

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.3174. Min Act: -0.0000

Data Index: 232460 (The Pile)

Max Activating Token Index: 1011

Text #3

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.1715. Min Act: -0.0000

Data Index: 1659580 (The Pile)

Max Activating Token Index: 797

Text #4

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.2374. Min Act: -0.0000

Data Index: 1785568 (The Pile)

Max Activating Token Index: 337

Text #5

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.2906. Min Act: -0.0000

Data Index: 128910 (The Pile)

Max Activating Token Index: 237

Text #6

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.3650. Min Act: -0.0000

Data Index: 953591 (The Pile)

Max Activating Token Index: 980

Text #7

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.1642. Min Act: -0.0000

Data Index: 620377 (The Pile)

Max Activating Token Index: 677

Text #8

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.1666. Min Act: -0.0000

Data Index: 203193 (The Pile)

Max Activating Token Index: 794

Text #9

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.1704. Min Act: -0.0000

Data Index: 802503 (The Pile)

Max Activating Token Index: 400

Text #10

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.0981. Min Act: -0.0000

Data Index: 359865 (The Pile)

Max Activating Token Index: 569

Text #11

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.0855. Min Act: -0.0000

Data Index: 730834 (The Pile)

Max Activating Token Index: 493

Text #12

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.1038. Min Act: -0.0000

Data Index: 178310 (The Pile)

Max Activating Token Index: 365

Text #13

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.1130. Min Act: -0.0000

Data Index: 1167297 (The Pile)

Max Activating Token Index: 851

Text #14

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.0639. Min Act: -0.0000

Data Index: 1684109 (The Pile)

Max Activating Token Index: 521

Text #15

Max Range: 1.6467. Min Range: -1.6467

Max Act: 0.9801. Min Act: -0.0000

Data Index: 447046 (The Pile)

Max Activating Token Index: 278

Text #16

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.0617. Min Act: -0.0000

Data Index: 1267995 (The Pile)

Max Activating Token Index: 292

Text #17

Max Range: 1.6467. Min Range: -1.6467

Max Act: 0.9477. Min Act: -0.0000

Data Index: 882080 (The Pile)

Max Activating Token Index: 904

Text #18

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.1292. Min Act: -0.0000

Data Index: 1391287 (The Pile)

Max Activating Token Index: 993

Text #19

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.0265. Min Act: -0.0000

Data Index: 901968 (The Pile)

Max Activating Token Index: 164