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

Dataset: The Pile

Neuron 2085 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2816. Min Range: -1.2816

Max Act: 1.2816. Min Act: -0.0000

Data Index: 1178856 (The Pile)

Max Activating Token Index: 299

Text #1

Max Range: 1.2816. Min Range: -1.2816

Max Act: 1.2768. Min Act: -0.0000

Data Index: 391438 (The Pile)

Max Activating Token Index: 528

Text #2

Max Range: 1.2816. Min Range: -1.2816

Max Act: 1.2230. Min Act: -0.0000

Data Index: 816821 (The Pile)

Max Activating Token Index: 590

Text #3

Max Range: 1.2816. Min Range: -1.2816

Max Act: 1.1441. Min Act: -0.0000

Data Index: 1345294 (The Pile)

Max Activating Token Index: 933

Text #4

Max Range: 1.2816. Min Range: -1.2816

Max Act: 1.2425. Min Act: -0.0000

Data Index: 1518760 (The Pile)

Max Activating Token Index: 402

Text #5

Max Range: 1.2816. Min Range: -1.2816

Max Act: 1.1106. Min Act: -0.0000

Data Index: 232536 (The Pile)

Max Activating Token Index: 970

Text #6

Max Range: 1.2816. Min Range: -1.2816

Max Act: 1.1602. Min Act: -0.0000

Data Index: 1850036 (The Pile)

Max Activating Token Index: 562

Text #7

Max Range: 1.2816. Min Range: -1.2816

Max Act: 1.1594. Min Act: -0.0000

Data Index: 1138405 (The Pile)

Max Activating Token Index: 280

Text #8

Max Range: 1.2816. Min Range: -1.2816

Max Act: 1.2220. Min Act: -0.0000

Data Index: 871100 (The Pile)

Max Activating Token Index: 866

Text #9

Max Range: 1.2816. Min Range: -1.2816

Max Act: 1.1457. Min Act: -0.0000

Data Index: 227523 (The Pile)

Max Activating Token Index: 709

Text #10

Max Range: 1.2816. Min Range: -1.2816

Max Act: 1.1389. Min Act: -0.0000

Data Index: 642225 (The Pile)

Max Activating Token Index: 96

Text #11

Max Range: 1.2816. Min Range: -1.2816

Max Act: 1.0732. Min Act: -0.0000

Data Index: 293549 (The Pile)

Max Activating Token Index: 914

Text #12

Max Range: 1.2816. Min Range: -1.2816

Max Act: 1.1558. Min Act: -0.0000

Data Index: 392216 (The Pile)

Max Activating Token Index: 417

Text #13

Max Range: 1.2816. Min Range: -1.2816

Max Act: 1.1815. Min Act: -0.0000

Data Index: 1524263 (The Pile)

Max Activating Token Index: 687

Text #14

Max Range: 1.2816. Min Range: -1.2816

Max Act: 1.0510. Min Act: -0.0000

Data Index: 298660 (The Pile)

Max Activating Token Index: 691

Text #15

Max Range: 1.2816. Min Range: -1.2816

Max Act: 1.0997. Min Act: -0.0000

Data Index: 1223007 (The Pile)

Max Activating Token Index: 936

Text #16

Max Range: 1.2816. Min Range: -1.2816

Max Act: 1.0527. Min Act: -0.0000

Data Index: 1956546 (The Pile)

Max Activating Token Index: 456

Text #17

Max Range: 1.2816. Min Range: -1.2816

Max Act: 1.0913. Min Act: -0.0000

Data Index: 623980 (The Pile)

Max Activating Token Index: 242

Text #18

Max Range: 1.2816. Min Range: -1.2816

Max Act: 1.0192. Min Act: -0.0000

Data Index: 721725 (The Pile)

Max Activating Token Index: 570

Text #19

Max Range: 1.2816. Min Range: -1.2816

Max Act: 1.0251. Min Act: -0.0000

Data Index: 1694878 (The Pile)

Max Activating Token Index: 908