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

Dataset: The Pile

Neuron 3141 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1015. Min Range: -4.1015

Max Act: 4.1015. Min Act: -0.0000

Data Index: 202250 (The Pile)

Max Activating Token Index: 375

Text #1

Max Range: 4.1015. Min Range: -4.1015

Max Act: 3.7721. Min Act: -0.0000

Data Index: 1193963 (The Pile)

Max Activating Token Index: 675

Text #2

Max Range: 4.1015. Min Range: -4.1015

Max Act: 3.6598. Min Act: -0.0000

Data Index: 1572388 (The Pile)

Max Activating Token Index: 894

Text #3

Max Range: 4.1015. Min Range: -4.1015

Max Act: 3.4224. Min Act: -0.0000

Data Index: 1078559 (The Pile)

Max Activating Token Index: 1018

Text #4

Max Range: 4.1015. Min Range: -4.1015

Max Act: 3.7329. Min Act: -0.0000

Data Index: 1055858 (The Pile)

Max Activating Token Index: 850

Text #5

Max Range: 4.1015. Min Range: -4.1015

Max Act: 3.6530. Min Act: -0.0000

Data Index: 882019 (The Pile)

Max Activating Token Index: 616

Text #6

Max Range: 4.1015. Min Range: -4.1015

Max Act: 3.3383. Min Act: -0.0000

Data Index: 534566 (The Pile)

Max Activating Token Index: 764

Text #7

Max Range: 4.1015. Min Range: -4.1015

Max Act: 3.3056. Min Act: -0.0000

Data Index: 1132653 (The Pile)

Max Activating Token Index: 382

Text #8

Max Range: 4.1015. Min Range: -4.1015

Max Act: 3.2838. Min Act: -0.0000

Data Index: 128446 (The Pile)

Max Activating Token Index: 487

Text #9

Max Range: 4.1015. Min Range: -4.1015

Max Act: 3.2751. Min Act: -0.0000

Data Index: 1300080 (The Pile)

Max Activating Token Index: 303

Text #10

Max Range: 4.1015. Min Range: -4.1015

Max Act: 3.2629. Min Act: -0.0000

Data Index: 172411 (The Pile)

Max Activating Token Index: 480

Text #11

Max Range: 4.1015. Min Range: -4.1015

Max Act: 3.3905. Min Act: -0.0000

Data Index: 533524 (The Pile)

Max Activating Token Index: 494

Text #12

Max Range: 4.1015. Min Range: -4.1015

Max Act: 3.3696. Min Act: -0.0000

Data Index: 1308478 (The Pile)

Max Activating Token Index: 424

Text #13

Max Range: 4.1015. Min Range: -4.1015

Max Act: 2.9125. Min Act: -0.0000

Data Index: 799520 (The Pile)

Max Activating Token Index: 717

Text #14

Max Range: 4.1015. Min Range: -4.1015

Max Act: 3.0245. Min Act: -0.0000

Data Index: 622380 (The Pile)

Max Activating Token Index: 352

Text #15

Max Range: 4.1015. Min Range: -4.1015

Max Act: 3.1787. Min Act: -0.0000

Data Index: 1964344 (The Pile)

Max Activating Token Index: 627

Text #16

Max Range: 4.1015. Min Range: -4.1015

Max Act: 3.1111. Min Act: -0.0000

Data Index: 1739270 (The Pile)

Max Activating Token Index: 432

Text #17

Max Range: 4.1015. Min Range: -4.1015

Max Act: 2.6931. Min Act: -0.0000

Data Index: 1839649 (The Pile)

Max Activating Token Index: 597

Text #18

Max Range: 4.1015. Min Range: -4.1015

Max Act: 3.2186. Min Act: -0.0000

Data Index: 510382 (The Pile)

Max Activating Token Index: 319

Text #19

Max Range: 4.1015. Min Range: -4.1015

Max Act: 2.8079. Min Act: -0.0000

Data Index: 1235611 (The Pile)

Max Activating Token Index: 846