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

Dataset: The Pile

Neuron 1222 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3509. Min Range: -3.3509

Max Act: 3.3509. Min Act: -0.0000

Data Index: 799891 (The Pile)

Max Activating Token Index: 554

Text #1

Max Range: 3.3509. Min Range: -3.3509

Max Act: 2.6460. Min Act: -0.0000

Data Index: 459884 (The Pile)

Max Activating Token Index: 155

Text #2

Max Range: 3.3509. Min Range: -3.3509

Max Act: 2.5264. Min Act: -0.0000

Data Index: 498814 (The Pile)

Max Activating Token Index: 885

Text #3

Max Range: 3.3509. Min Range: -3.3509

Max Act: 2.4919. Min Act: -0.0000

Data Index: 13276 (The Pile)

Max Activating Token Index: 286

Text #4

Max Range: 3.3509. Min Range: -3.3509

Max Act: 2.3614. Min Act: -0.0000

Data Index: 530529 (The Pile)

Max Activating Token Index: 655

Text #5

Max Range: 3.3509. Min Range: -3.3509

Max Act: 2.0331. Min Act: -0.0000

Data Index: 875446 (The Pile)

Max Activating Token Index: 765

Text #6

Max Range: 3.3509. Min Range: -3.3509

Max Act: 1.8817. Min Act: -0.0000

Data Index: 243005 (The Pile)

Max Activating Token Index: 441

Text #7

Max Range: 3.3509. Min Range: -3.3509

Max Act: 1.8654. Min Act: -0.0000

Data Index: 1126886 (The Pile)

Max Activating Token Index: 516

Text #8

Max Range: 3.3509. Min Range: -3.3509

Max Act: 1.8443. Min Act: -0.0000

Data Index: 330569 (The Pile)

Max Activating Token Index: 234

Text #9

Max Range: 3.3509. Min Range: -3.3509

Max Act: 1.8179. Min Act: -0.0000

Data Index: 1374393 (The Pile)

Max Activating Token Index: 101

Text #10

Max Range: 3.3509. Min Range: -3.3509

Max Act: 1.8172. Min Act: -0.0000

Data Index: 1705695 (The Pile)

Max Activating Token Index: 501

Text #11

Max Range: 3.3509. Min Range: -3.3509

Max Act: 1.8106. Min Act: -0.0000

Data Index: 1612916 (The Pile)

Max Activating Token Index: 492

Text #12

Max Range: 3.3509. Min Range: -3.3509

Max Act: 1.7076. Min Act: -0.0000

Data Index: 1671104 (The Pile)

Max Activating Token Index: 741

Text #13

Max Range: 3.3509. Min Range: -3.3509

Max Act: 1.5593. Min Act: -0.0000

Data Index: 1277085 (The Pile)

Max Activating Token Index: 872

Text #14

Max Range: 3.3509. Min Range: -3.3509

Max Act: 1.7056. Min Act: -0.0000

Data Index: 47448 (The Pile)

Max Activating Token Index: 137

Text #15

Max Range: 3.3509. Min Range: -3.3509

Max Act: 1.7977. Min Act: -0.0000

Data Index: 1933957 (The Pile)

Max Activating Token Index: 311

Text #16

Max Range: 3.3509. Min Range: -3.3509

Max Act: 1.7192. Min Act: -0.0000

Data Index: 1526226 (The Pile)

Max Activating Token Index: 955

Text #17

Max Range: 3.3509. Min Range: -3.3509

Max Act: 1.7105. Min Act: -0.0000

Data Index: 1756071 (The Pile)

Max Activating Token Index: 501

Text #18

Max Range: 3.3509. Min Range: -3.3509

Max Act: 1.7365. Min Act: -0.0000

Data Index: 1856525 (The Pile)

Max Activating Token Index: 199

Text #19

Max Range: 3.3509. Min Range: -3.3509

Max Act: 1.7631. Min Act: -0.0000

Data Index: 1170991 (The Pile)

Max Activating Token Index: 597