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

Dataset: The Pile

Neuron 4302 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: 4.3808. Min Range: -4.3808

Max Act: 4.3808. Min Act: -0.0000

Data Index: 932497 (The Pile)

Max Activating Token Index: 844

Text #1

Max Range: 4.3808. Min Range: -4.3808

Max Act: 3.6683. Min Act: -0.0000

Data Index: 712550 (The Pile)

Max Activating Token Index: 606

Text #2

Max Range: 4.3808. Min Range: -4.3808

Max Act: 3.5970. Min Act: -0.0000

Data Index: 1340404 (The Pile)

Max Activating Token Index: 568

Text #3

Max Range: 4.3808. Min Range: -4.3808

Max Act: 3.7570. Min Act: -0.0000

Data Index: 1327293 (The Pile)

Max Activating Token Index: 1009

Text #4

Max Range: 4.3808. Min Range: -4.3808

Max Act: 3.3723. Min Act: -0.0000

Data Index: 1298396 (The Pile)

Max Activating Token Index: 283

Text #5

Max Range: 4.3808. Min Range: -4.3808

Max Act: 3.2458. Min Act: -0.0000

Data Index: 1188508 (The Pile)

Max Activating Token Index: 328

Text #6

Max Range: 4.3808. Min Range: -4.3808

Max Act: 3.1874. Min Act: -0.0000

Data Index: 559260 (The Pile)

Max Activating Token Index: 218

Text #7

Max Range: 4.3808. Min Range: -4.3808

Max Act: 3.3513. Min Act: -0.0000

Data Index: 1821035 (The Pile)

Max Activating Token Index: 205

Text #8

Max Range: 4.3808. Min Range: -4.3808

Max Act: 3.1601. Min Act: -0.0000

Data Index: 882424 (The Pile)

Max Activating Token Index: 338

Text #9

Max Range: 4.3808. Min Range: -4.3808

Max Act: 2.9696. Min Act: -0.0000

Data Index: 602342 (The Pile)

Max Activating Token Index: 935

Text #10

Max Range: 4.3808. Min Range: -4.3808

Max Act: 3.2567. Min Act: -0.0000

Data Index: 1241906 (The Pile)

Max Activating Token Index: 636

Text #11

Max Range: 4.3808. Min Range: -4.3808

Max Act: 2.6760. Min Act: -0.0000

Data Index: 260763 (The Pile)

Max Activating Token Index: 920

Text #12

Max Range: 4.3808. Min Range: -4.3808

Max Act: 3.0729. Min Act: -0.0000

Data Index: 929606 (The Pile)

Max Activating Token Index: 871

Text #13

Max Range: 4.3808. Min Range: -4.3808

Max Act: 2.7961. Min Act: -0.0000

Data Index: 1225404 (The Pile)

Max Activating Token Index: 700

Text #14

Max Range: 4.3808. Min Range: -4.3808

Max Act: 2.7356. Min Act: -0.0000

Data Index: 190075 (The Pile)

Max Activating Token Index: 505

Text #15

Max Range: 4.3808. Min Range: -4.3808

Max Act: 2.9108. Min Act: -0.0000

Data Index: 1345121 (The Pile)

Max Activating Token Index: 827

Text #16

Max Range: 4.3808. Min Range: -4.3808

Max Act: 2.7465. Min Act: -0.0000

Data Index: 901917 (The Pile)

Max Activating Token Index: 410

Text #17

Max Range: 4.3808. Min Range: -4.3808

Max Act: 2.5776. Min Act: -0.0000

Data Index: 1973576 (The Pile)

Max Activating Token Index: 281

Text #18

Max Range: 4.3808. Min Range: -4.3808

Max Act: 2.6857. Min Act: -0.0000

Data Index: 969357 (The Pile)

Max Activating Token Index: 496

Text #19

Max Range: 4.3808. Min Range: -4.3808

Max Act: 2.6788. Min Act: -0.0000

Data Index: 412491 (The Pile)

Max Activating Token Index: 224