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

Dataset: The Pile

Neuron 4710 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: 0.8629. Min Range: -0.8629

Max Act: 0.8629. Min Act: -0.0000

Data Index: 264269 (The Pile)

Max Activating Token Index: 598

Text #1

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.8080. Min Act: -0.0000

Data Index: 596443 (The Pile)

Max Activating Token Index: 142

Text #2

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.7662. Min Act: -0.0000

Data Index: 471972 (The Pile)

Max Activating Token Index: 777

Text #3

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.7016. Min Act: -0.0000

Data Index: 1332206 (The Pile)

Max Activating Token Index: 900

Text #4

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.6351. Min Act: -0.0000

Data Index: 1398649 (The Pile)

Max Activating Token Index: 740

Text #5

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.6314. Min Act: -0.0000

Data Index: 7531 (The Pile)

Max Activating Token Index: 901

Text #6

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5816. Min Act: -0.0000

Data Index: 1710238 (The Pile)

Max Activating Token Index: 568

Text #7

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5801. Min Act: -0.0000

Data Index: 1756220 (The Pile)

Max Activating Token Index: 219

Text #8

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5682. Min Act: -0.0000

Data Index: 1038824 (The Pile)

Max Activating Token Index: 1011

Text #9

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5637. Min Act: -0.0000

Data Index: 360003 (The Pile)

Max Activating Token Index: 474

Text #10

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5769. Min Act: -0.0000

Data Index: 1414697 (The Pile)

Max Activating Token Index: 279

Text #11

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5443. Min Act: -0.0000

Data Index: 118234 (The Pile)

Max Activating Token Index: 537

Text #12

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5125. Min Act: -0.0000

Data Index: 1591399 (The Pile)

Max Activating Token Index: 747

Text #13

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5243. Min Act: -0.0000

Data Index: 1440847 (The Pile)

Max Activating Token Index: 602

Text #14

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5395. Min Act: -0.0000

Data Index: 589765 (The Pile)

Max Activating Token Index: 671

Text #15

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5312. Min Act: -0.0000

Data Index: 832046 (The Pile)

Max Activating Token Index: 687

Text #16

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.4875. Min Act: -0.0000

Data Index: 1894366 (The Pile)

Max Activating Token Index: 711

Text #17

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.4897. Min Act: -0.0000

Data Index: 1631672 (The Pile)

Max Activating Token Index: 777

Text #18

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5171. Min Act: -0.0000

Data Index: 430896 (The Pile)

Max Activating Token Index: 870

Text #19

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5064. Min Act: -0.0000

Data Index: 1035115 (The Pile)

Max Activating Token Index: 821