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

Dataset: The Pile

Neuron 3976 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: 1.3997. Min Range: -1.3997

Max Act: 1.2268. Min Act: -0.0000

Data Index: 815386 (The Pile)

Max Activating Token Index: 726

Text #1

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.3997. Min Act: -0.0000

Data Index: 169910 (The Pile)

Max Activating Token Index: 423

Text #2

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.3857. Min Act: -0.0000

Data Index: 680176 (The Pile)

Max Activating Token Index: 735

Text #3

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.2312. Min Act: -0.0000

Data Index: 1592701 (The Pile)

Max Activating Token Index: 814

Text #4

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.1926. Min Act: -0.0000

Data Index: 484926 (The Pile)

Max Activating Token Index: 224

Text #5

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.2621. Min Act: -0.0000

Data Index: 1297504 (The Pile)

Max Activating Token Index: 308

Text #6

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.2368. Min Act: -0.0000

Data Index: 1989655 (The Pile)

Max Activating Token Index: 340

Text #7

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.2202. Min Act: -0.0000

Data Index: 1721538 (The Pile)

Max Activating Token Index: 842

Text #8

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.0471. Min Act: -0.0000

Data Index: 1021649 (The Pile)

Max Activating Token Index: 821

Text #9

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.1032. Min Act: -0.0000

Data Index: 1523369 (The Pile)

Max Activating Token Index: 143

Text #10

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.0013. Min Act: -0.0000

Data Index: 808361 (The Pile)

Max Activating Token Index: 333

Text #11

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.0939. Min Act: -0.0000

Data Index: 426156 (The Pile)

Max Activating Token Index: 339

Text #12

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.0852. Min Act: -0.0000

Data Index: 229423 (The Pile)

Max Activating Token Index: 293

Text #13

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.0783. Min Act: -0.0000

Data Index: 1281757 (The Pile)

Max Activating Token Index: 952

Text #14

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.0219. Min Act: -0.0000

Data Index: 1252798 (The Pile)

Max Activating Token Index: 139

Text #15

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.0059. Min Act: -0.0000

Data Index: 1312437 (The Pile)

Max Activating Token Index: 579

Text #16

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.1328. Min Act: -0.0000

Data Index: 1556965 (The Pile)

Max Activating Token Index: 33

Text #17

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.0344. Min Act: -0.0000

Data Index: 1831269 (The Pile)

Max Activating Token Index: 266

Text #18

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.0952. Min Act: -0.0000

Data Index: 604906 (The Pile)

Max Activating Token Index: 371

Text #19

Max Range: 1.3997. Min Range: -1.3997

Max Act: 1.0755. Min Act: -0.0000

Data Index: 1489111 (The Pile)

Max Activating Token Index: 865