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

Dataset: The Pile

Neuron 1517 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.2318. Min Act: -0.0001

Data Index: 1137954 (The Pile)

Max Activating Token Index: 456

Text #1

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.2271. Min Act: -0.0000

Data Index: 794271 (The Pile)

Max Activating Token Index: 281

Text #2

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.2186. Min Act: -0.0000

Data Index: 1579843 (The Pile)

Max Activating Token Index: 458

Text #3

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.2029. Min Act: -0.0000

Data Index: 200871 (The Pile)

Max Activating Token Index: 913

Text #4

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.2047. Min Act: -0.0000

Data Index: 138725 (The Pile)

Max Activating Token Index: 942

Text #5

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.1756. Min Act: -0.0000

Data Index: 820625 (The Pile)

Max Activating Token Index: 251

Text #6

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.1865. Min Act: -0.0000

Data Index: 175328 (The Pile)

Max Activating Token Index: 871

Text #7

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.1833. Min Act: -0.0000

Data Index: 1219900 (The Pile)

Max Activating Token Index: 324

Text #8

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.1923. Min Act: -0.0000

Data Index: 670925 (The Pile)

Max Activating Token Index: 865

Text #9

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.1847. Min Act: -0.0000

Data Index: 760617 (The Pile)

Max Activating Token Index: 319

Text #10

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.2164. Min Act: -0.0000

Data Index: 1592962 (The Pile)

Max Activating Token Index: 842

Text #11

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.1805. Min Act: -0.0000

Data Index: 64645 (The Pile)

Max Activating Token Index: 361

Text #12

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.1495. Min Act: -0.0000

Data Index: 1094470 (The Pile)

Max Activating Token Index: 916

Text #13

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.1725. Min Act: -0.0000

Data Index: 1997356 (The Pile)

Max Activating Token Index: 688

Text #14

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.1673. Min Act: -0.0000

Data Index: 877420 (The Pile)

Max Activating Token Index: 577

Text #15

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.1681. Min Act: -0.0000

Data Index: 1903711 (The Pile)

Max Activating Token Index: 773

Text #16

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.1700. Min Act: -0.0000

Data Index: 1737738 (The Pile)

Max Activating Token Index: 801

Text #17

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.1722. Min Act: -0.0000

Data Index: 340411 (The Pile)

Max Activating Token Index: 330

Text #18

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.1587. Min Act: -0.0000

Data Index: 415614 (The Pile)

Max Activating Token Index: 591

Text #19

Max Range: 0.2318. Min Range: -0.2318

Max Act: 0.1679. Min Act: -0.0000

Data Index: 1793826 (The Pile)

Max Activating Token Index: 323