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

Dataset: The Pile

Neuron 403 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: 0.1428. Min Range: -0.1428

Max Act: 0.1428. Min Act: -0.0000

Data Index: 787402 (The Pile)

Max Activating Token Index: 189

Text #1

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1392. Min Act: -0.0000

Data Index: 1108632 (The Pile)

Max Activating Token Index: 219

Text #2

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1137. Min Act: -0.0000

Data Index: 1862901 (The Pile)

Max Activating Token Index: 676

Text #3

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1119. Min Act: -0.0000

Data Index: 1744372 (The Pile)

Max Activating Token Index: 503

Text #4

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1063. Min Act: -0.0000

Data Index: 1087464 (The Pile)

Max Activating Token Index: 1006

Text #5

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1043. Min Act: -0.0000

Data Index: 33374 (The Pile)

Max Activating Token Index: 759

Text #6

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1246. Min Act: -0.0000

Data Index: 1531961 (The Pile)

Max Activating Token Index: 958

Text #7

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1140. Min Act: -0.0000

Data Index: 1052098 (The Pile)

Max Activating Token Index: 310

Text #8

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1054. Min Act: -0.0000

Data Index: 1689708 (The Pile)

Max Activating Token Index: 709

Text #9

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1087. Min Act: -0.0000

Data Index: 1294816 (The Pile)

Max Activating Token Index: 807

Text #10

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1099. Min Act: -0.0000

Data Index: 1883486 (The Pile)

Max Activating Token Index: 659

Text #11

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1031. Min Act: -0.0000

Data Index: 1750434 (The Pile)

Max Activating Token Index: 374

Text #12

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1050. Min Act: -0.0000

Data Index: 1644682 (The Pile)

Max Activating Token Index: 524

Text #13

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0890. Min Act: -0.0000

Data Index: 648019 (The Pile)

Max Activating Token Index: 659

Text #14

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.1126. Min Act: -0.0000

Data Index: 1004700 (The Pile)

Max Activating Token Index: 874

Text #15

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0972. Min Act: -0.0000

Data Index: 1952277 (The Pile)

Max Activating Token Index: 720

Text #16

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0941. Min Act: -0.0000

Data Index: 139219 (The Pile)

Max Activating Token Index: 386

Text #17

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0994. Min Act: -0.0000

Data Index: 1938095 (The Pile)

Max Activating Token Index: 485

Text #18

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0919. Min Act: -0.0000

Data Index: 10095 (The Pile)

Max Activating Token Index: 439

Text #19

Max Range: 0.1428. Min Range: -0.1428

Max Act: 0.0703. Min Act: -0.0000

Data Index: 1513140 (The Pile)

Max Activating Token Index: 101