Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2380 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1619. Min Act: -0.0000

Data Index: 517255 (The Pile)

Max Activating Token Index: 607

Text #1

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1580. Min Act: -0.0000

Data Index: 169760 (The Pile)

Max Activating Token Index: 492

Text #2

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1401. Min Act: -0.0000

Data Index: 997043 (The Pile)

Max Activating Token Index: 191

Text #3

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1543. Min Act: -0.0000

Data Index: 141723 (The Pile)

Max Activating Token Index: 265

Text #4

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1252. Min Act: -0.0000

Data Index: 1508631 (The Pile)

Max Activating Token Index: 837

Text #5

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1162. Min Act: -0.0000

Data Index: 717732 (The Pile)

Max Activating Token Index: 170

Text #6

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1149. Min Act: -0.0000

Data Index: 166230 (The Pile)

Max Activating Token Index: 837

Text #7

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1076. Min Act: -0.0000

Data Index: 465332 (The Pile)

Max Activating Token Index: 952

Text #8

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1045. Min Act: -0.0000

Data Index: 740891 (The Pile)

Max Activating Token Index: 458

Text #9

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1043. Min Act: -0.0000

Data Index: 1956502 (The Pile)

Max Activating Token Index: 260

Text #10

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1019. Min Act: -0.0000

Data Index: 1175684 (The Pile)

Max Activating Token Index: 633

Text #11

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.0873. Min Act: -0.0000

Data Index: 91505 (The Pile)

Max Activating Token Index: 162

Text #12

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.0935. Min Act: -0.0000

Data Index: 1878742 (The Pile)

Max Activating Token Index: 1010

Text #13

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.0884. Min Act: -0.0000

Data Index: 1621679 (The Pile)

Max Activating Token Index: 558

Text #14

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1000. Min Act: -0.0000

Data Index: 1226594 (The Pile)

Max Activating Token Index: 495

Text #15

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.1004. Min Act: -0.0000

Data Index: 1658356 (The Pile)

Max Activating Token Index: 933

Text #16

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.0911. Min Act: -0.0000

Data Index: 1400682 (The Pile)

Max Activating Token Index: 814

Text #17

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.0863. Min Act: -0.0000

Data Index: 653668 (The Pile)

Max Activating Token Index: 248

Text #18

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.0923. Min Act: -0.0000

Data Index: 1320200 (The Pile)

Max Activating Token Index: 399

Text #19

Max Range: 0.1619. Min Range: -0.1619

Max Act: 0.0912. Min Act: -0.0000

Data Index: 1074722 (The Pile)

Max Activating Token Index: 111