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

Dataset: The Pile

Neuron 1787 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.6671. Min Act: -0.0000

Data Index: 494171 (The Pile)

Max Activating Token Index: 772

Text #1

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.2133. Min Act: -0.0000

Data Index: 266084 (The Pile)

Max Activating Token Index: 174

Text #2

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.4634. Min Act: -0.0000

Data Index: 1472009 (The Pile)

Max Activating Token Index: 469

Text #3

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.4309. Min Act: -0.0000

Data Index: 1113342 (The Pile)

Max Activating Token Index: 922

Text #4

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.3925. Min Act: -0.0000

Data Index: 873754 (The Pile)

Max Activating Token Index: 890

Text #5

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.2200. Min Act: -0.0000

Data Index: 1082534 (The Pile)

Max Activating Token Index: 94

Text #6

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.0646. Min Act: -0.0000

Data Index: 1265188 (The Pile)

Max Activating Token Index: 383

Text #7

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.1160. Min Act: -0.0000

Data Index: 1793368 (The Pile)

Max Activating Token Index: 524

Text #8

Max Range: 1.6671. Min Range: -1.6671

Max Act: 0.8879. Min Act: -0.0000

Data Index: 1849460 (The Pile)

Max Activating Token Index: 903

Text #9

Max Range: 1.6671. Min Range: -1.6671

Max Act: 0.9954. Min Act: -0.0000

Data Index: 1726467 (The Pile)

Max Activating Token Index: 765

Text #10

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.1285. Min Act: -0.0000

Data Index: 253203 (The Pile)

Max Activating Token Index: 944

Text #11

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.0619. Min Act: -0.0000

Data Index: 1854013 (The Pile)

Max Activating Token Index: 662

Text #12

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.1038. Min Act: -0.0000

Data Index: 1633030 (The Pile)

Max Activating Token Index: 51

Text #13

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.1058. Min Act: -0.0000

Data Index: 920100 (The Pile)

Max Activating Token Index: 293

Text #14

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.0750. Min Act: -0.0000

Data Index: 305422 (The Pile)

Max Activating Token Index: 278

Text #15

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.0615. Min Act: -0.0000

Data Index: 494863 (The Pile)

Max Activating Token Index: 694

Text #16

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.0131. Min Act: -0.0000

Data Index: 305390 (The Pile)

Max Activating Token Index: 677

Text #17

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.1199. Min Act: -0.0000

Data Index: 1715685 (The Pile)

Max Activating Token Index: 933

Text #18

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.0189. Min Act: -0.0000

Data Index: 359690 (The Pile)

Max Activating Token Index: 354

Text #19

Max Range: 1.6671. Min Range: -1.6671

Max Act: 1.0402. Min Act: -0.0000

Data Index: 35906 (The Pile)

Max Activating Token Index: 875