Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1788 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.8624. Min Act: -0.0000

Data Index: 992146 (The Pile)

Max Activating Token Index: 612

Text #1

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.8918. Min Act: -0.0000

Data Index: 1199253 (The Pile)

Max Activating Token Index: 142

Text #2

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.7063. Min Act: -0.0000

Data Index: 1922780 (The Pile)

Max Activating Token Index: 967

Text #3

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.6733. Min Act: -0.0000

Data Index: 750436 (The Pile)

Max Activating Token Index: 913

Text #4

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.6113. Min Act: -0.0000

Data Index: 1408424 (The Pile)

Max Activating Token Index: 49

Text #5

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.6438. Min Act: -0.0000

Data Index: 665477 (The Pile)

Max Activating Token Index: 697

Text #6

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.6233. Min Act: -0.0000

Data Index: 1917089 (The Pile)

Max Activating Token Index: 108

Text #7

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.6293. Min Act: -0.0000

Data Index: 460609 (The Pile)

Max Activating Token Index: 833

Text #8

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.5990. Min Act: -0.0000

Data Index: 1801268 (The Pile)

Max Activating Token Index: 938

Text #9

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.6570. Min Act: -0.0000

Data Index: 1623332 (The Pile)

Max Activating Token Index: 522

Text #10

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.6373. Min Act: -0.0000

Data Index: 535149 (The Pile)

Max Activating Token Index: 498

Text #11

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.5883. Min Act: -0.0000

Data Index: 1844215 (The Pile)

Max Activating Token Index: 703

Text #12

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.6427. Min Act: -0.0000

Data Index: 725917 (The Pile)

Max Activating Token Index: 549

Text #13

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.5912. Min Act: -0.0000

Data Index: 1550815 (The Pile)

Max Activating Token Index: 669

Text #14

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.6098. Min Act: -0.0000

Data Index: 1679051 (The Pile)

Max Activating Token Index: 772

Text #15

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.5324. Min Act: -0.0000

Data Index: 1757826 (The Pile)

Max Activating Token Index: 639

Text #16

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.5513. Min Act: -0.0000

Data Index: 951703 (The Pile)

Max Activating Token Index: 346

Text #17

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.5722. Min Act: -0.0000

Data Index: 257564 (The Pile)

Max Activating Token Index: 560

Text #18

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.5650. Min Act: -0.0000

Data Index: 22460 (The Pile)

Max Activating Token Index: 270

Text #19

Max Range: 0.8918. Min Range: -0.8918

Max Act: 0.6115. Min Act: -0.0000

Data Index: 1250179 (The Pile)

Max Activating Token Index: 448