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

Dataset: The Pile

Neuron 3773 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: 4.8087. Min Range: -4.8087

Max Act: 4.8087. Min Act: -0.0000

Data Index: 1815327 (The Pile)

Max Activating Token Index: 385

Text #1

Max Range: 4.8087. Min Range: -4.8087

Max Act: 4.2596. Min Act: -0.0000

Data Index: 1296759 (The Pile)

Max Activating Token Index: 404

Text #2

Max Range: 4.8087. Min Range: -4.8087

Max Act: 4.0665. Min Act: -0.0000

Data Index: 1394130 (The Pile)

Max Activating Token Index: 47

Text #3

Max Range: 4.8087. Min Range: -4.8087

Max Act: 4.4112. Min Act: -0.0000

Data Index: 1329305 (The Pile)

Max Activating Token Index: 762

Text #4

Max Range: 4.8087. Min Range: -4.8087

Max Act: 4.1734. Min Act: -0.0000

Data Index: 957836 (The Pile)

Max Activating Token Index: 395

Text #5

Max Range: 4.8087. Min Range: -4.8087

Max Act: 4.2761. Min Act: -0.0000

Data Index: 854521 (The Pile)

Max Activating Token Index: 278

Text #6

Max Range: 4.8087. Min Range: -4.8087

Max Act: 4.0939. Min Act: -0.0000

Data Index: 1003814 (The Pile)

Max Activating Token Index: 26

Text #7

Max Range: 4.8087. Min Range: -4.8087

Max Act: 4.1044. Min Act: -0.0000

Data Index: 1488549 (The Pile)

Max Activating Token Index: 414

Text #8

Max Range: 4.8087. Min Range: -4.8087

Max Act: 4.2212. Min Act: -0.0000

Data Index: 79364 (The Pile)

Max Activating Token Index: 420

Text #9

Max Range: 4.8087. Min Range: -4.8087

Max Act: 3.6824. Min Act: -0.0000

Data Index: 1368591 (The Pile)

Max Activating Token Index: 693

Text #10

Max Range: 4.8087. Min Range: -4.8087

Max Act: 3.7795. Min Act: -0.0000

Data Index: 1649098 (The Pile)

Max Activating Token Index: 759

Text #11

Max Range: 4.8087. Min Range: -4.8087

Max Act: 4.0283. Min Act: -0.0000

Data Index: 976078 (The Pile)

Max Activating Token Index: 772

Text #12

Max Range: 4.8087. Min Range: -4.8087

Max Act: 3.5550. Min Act: -0.0000

Data Index: 1800375 (The Pile)

Max Activating Token Index: 966

Text #13

Max Range: 4.8087. Min Range: -4.8087

Max Act: 3.3085. Min Act: -0.0000

Data Index: 1975210 (The Pile)

Max Activating Token Index: 930

Text #14

Max Range: 4.8087. Min Range: -4.8087

Max Act: 3.7791. Min Act: -0.0000

Data Index: 1762107 (The Pile)

Max Activating Token Index: 895

Text #15

Max Range: 4.8087. Min Range: -4.8087

Max Act: 3.7653. Min Act: -0.0000

Data Index: 1745499 (The Pile)

Max Activating Token Index: 450

Text #16

Max Range: 4.8087. Min Range: -4.8087

Max Act: 3.5824. Min Act: -0.0000

Data Index: 1177453 (The Pile)

Max Activating Token Index: 491

Text #17

Max Range: 4.8087. Min Range: -4.8087

Max Act: 3.7317. Min Act: -0.0000

Data Index: 316485 (The Pile)

Max Activating Token Index: 828

Text #18

Max Range: 4.8087. Min Range: -4.8087

Max Act: 3.2859. Min Act: -0.0000

Data Index: 1184065 (The Pile)

Max Activating Token Index: 837

Text #19

Max Range: 4.8087. Min Range: -4.8087

Max Act: 3.5454. Min Act: -0.0000

Data Index: 1311756 (The Pile)

Max Activating Token Index: 859