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

Dataset: The Pile

Neuron 2159 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: 1.4484. Min Range: -1.4484

Max Act: 1.4484. Min Act: -0.0000

Data Index: 1453422 (The Pile)

Max Activating Token Index: 59

Text #1

Max Range: 1.4484. Min Range: -1.4484

Max Act: 1.1845. Min Act: -0.0000

Data Index: 1361572 (The Pile)

Max Activating Token Index: 436

Text #2

Max Range: 1.4484. Min Range: -1.4484

Max Act: 1.2048. Min Act: -0.0000

Data Index: 107658 (The Pile)

Max Activating Token Index: 96

Text #3

Max Range: 1.4484. Min Range: -1.4484

Max Act: 1.1209. Min Act: -0.0000

Data Index: 290067 (The Pile)

Max Activating Token Index: 350

Text #4

Max Range: 1.4484. Min Range: -1.4484

Max Act: 1.0963. Min Act: -0.0000

Data Index: 86451 (The Pile)

Max Activating Token Index: 284

Text #5

Max Range: 1.4484. Min Range: -1.4484

Max Act: 1.1896. Min Act: -0.0000

Data Index: 725398 (The Pile)

Max Activating Token Index: 915

Text #6

Max Range: 1.4484. Min Range: -1.4484

Max Act: 1.0378. Min Act: -0.0000

Data Index: 1390156 (The Pile)

Max Activating Token Index: 973

Text #7

Max Range: 1.4484. Min Range: -1.4484

Max Act: 1.1488. Min Act: -0.0000

Data Index: 1587526 (The Pile)

Max Activating Token Index: 373

Text #8

Max Range: 1.4484. Min Range: -1.4484

Max Act: 1.0792. Min Act: -0.0000

Data Index: 1455609 (The Pile)

Max Activating Token Index: 958

Text #9

Max Range: 1.4484. Min Range: -1.4484

Max Act: 1.1181. Min Act: -0.0000

Data Index: 1458851 (The Pile)

Max Activating Token Index: 76

Text #10

Max Range: 1.4484. Min Range: -1.4484

Max Act: 1.1086. Min Act: -0.0000

Data Index: 1018902 (The Pile)

Max Activating Token Index: 607

Text #11

Max Range: 1.4484. Min Range: -1.4484

Max Act: 1.0390. Min Act: -0.0000

Data Index: 1187117 (The Pile)

Max Activating Token Index: 304

Text #12

Max Range: 1.4484. Min Range: -1.4484

Max Act: 1.1268. Min Act: -0.0000

Data Index: 840387 (The Pile)

Max Activating Token Index: 102

Text #13

Max Range: 1.4484. Min Range: -1.4484

Max Act: 1.0301. Min Act: -0.0000

Data Index: 1344982 (The Pile)

Max Activating Token Index: 469

Text #14

Max Range: 1.4484. Min Range: -1.4484

Max Act: 0.9607. Min Act: -0.0000

Data Index: 245187 (The Pile)

Max Activating Token Index: 804

Text #15

Max Range: 1.4484. Min Range: -1.4484

Max Act: 0.9031. Min Act: -0.0000

Data Index: 206166 (The Pile)

Max Activating Token Index: 237

Text #16

Max Range: 1.4484. Min Range: -1.4484

Max Act: 0.9389. Min Act: -0.0000

Data Index: 132846 (The Pile)

Max Activating Token Index: 904

Text #17

Max Range: 1.4484. Min Range: -1.4484

Max Act: 1.0503. Min Act: -0.0000

Data Index: 208381 (The Pile)

Max Activating Token Index: 1011

Text #18

Max Range: 1.4484. Min Range: -1.4484

Max Act: 0.9892. Min Act: -0.0000

Data Index: 977412 (The Pile)

Max Activating Token Index: 444

Text #19

Max Range: 1.4484. Min Range: -1.4484

Max Act: 0.9670. Min Act: -0.0000

Data Index: 1361424 (The Pile)

Max Activating Token Index: 182