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

Dataset: The Pile

Neuron 4760 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: 1.4803. Min Range: -1.4803

Max Act: 1.4803. Min Act: -0.0000

Data Index: 173478 (The Pile)

Max Activating Token Index: 1000

Text #1

Max Range: 1.4803. Min Range: -1.4803

Max Act: 1.3137. Min Act: -0.0000

Data Index: 556680 (The Pile)

Max Activating Token Index: 831

Text #2

Max Range: 1.4803. Min Range: -1.4803

Max Act: 1.2891. Min Act: -0.0000

Data Index: 1305541 (The Pile)

Max Activating Token Index: 60

Text #3

Max Range: 1.4803. Min Range: -1.4803

Max Act: 1.2411. Min Act: -0.0000

Data Index: 855139 (The Pile)

Max Activating Token Index: 716

Text #4

Max Range: 1.4803. Min Range: -1.4803

Max Act: 1.3137. Min Act: -0.0000

Data Index: 261535 (The Pile)

Max Activating Token Index: 654

Text #5

Max Range: 1.4803. Min Range: -1.4803

Max Act: 1.2169. Min Act: -0.0000

Data Index: 1688507 (The Pile)

Max Activating Token Index: 616

Text #6

Max Range: 1.4803. Min Range: -1.4803

Max Act: 1.1569. Min Act: -0.0000

Data Index: 101010 (The Pile)

Max Activating Token Index: 639

Text #7

Max Range: 1.4803. Min Range: -1.4803

Max Act: 1.0762. Min Act: -0.0000

Data Index: 1717587 (The Pile)

Max Activating Token Index: 716

Text #8

Max Range: 1.4803. Min Range: -1.4803

Max Act: 1.1667. Min Act: -0.0000

Data Index: 135188 (The Pile)

Max Activating Token Index: 498

Text #9

Max Range: 1.4803. Min Range: -1.4803

Max Act: 1.0581. Min Act: -0.0000

Data Index: 1967008 (The Pile)

Max Activating Token Index: 973

Text #10

Max Range: 1.4803. Min Range: -1.4803

Max Act: 1.0012. Min Act: -0.0001

Data Index: 1021541 (The Pile)

Max Activating Token Index: 749

Text #11

Max Range: 1.4803. Min Range: -1.4803

Max Act: 0.9936. Min Act: -0.0000

Data Index: 1769728 (The Pile)

Max Activating Token Index: 789

Text #12

Max Range: 1.4803. Min Range: -1.4803

Max Act: 1.1106. Min Act: -0.0000

Data Index: 1540051 (The Pile)

Max Activating Token Index: 999

Text #13

Max Range: 1.4803. Min Range: -1.4803

Max Act: 0.9416. Min Act: -0.0000

Data Index: 406404 (The Pile)

Max Activating Token Index: 820

Text #14

Max Range: 1.4803. Min Range: -1.4803

Max Act: 1.0628. Min Act: -0.0000

Data Index: 814989 (The Pile)

Max Activating Token Index: 362

Text #15

Max Range: 1.4803. Min Range: -1.4803

Max Act: 0.9322. Min Act: -0.0000

Data Index: 1772575 (The Pile)

Max Activating Token Index: 800

Text #16

Max Range: 1.4803. Min Range: -1.4803

Max Act: 1.0044. Min Act: -0.0000

Data Index: 1762084 (The Pile)

Max Activating Token Index: 1020

Text #17

Max Range: 1.4803. Min Range: -1.4803

Max Act: 1.0092. Min Act: -0.0000

Data Index: 565057 (The Pile)

Max Activating Token Index: 608

Text #18

Max Range: 1.4803. Min Range: -1.4803

Max Act: 0.9456. Min Act: -0.0001

Data Index: 1868158 (The Pile)

Max Activating Token Index: 882

Text #19

Max Range: 1.4803. Min Range: -1.4803

Max Act: 1.0617. Min Act: -0.0000

Data Index: 1371215 (The Pile)

Max Activating Token Index: 597