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

Dataset: The Pile

Neuron 4872 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: 1.5937. Min Range: -1.5937

Max Act: 1.5937. Min Act: -0.0000

Data Index: 423148 (The Pile)

Max Activating Token Index: 934

Text #1

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.5249. Min Act: -0.0000

Data Index: 1750642 (The Pile)

Max Activating Token Index: 411

Text #2

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.4206. Min Act: -0.0000

Data Index: 1154673 (The Pile)

Max Activating Token Index: 134

Text #3

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.4808. Min Act: -0.0000

Data Index: 386492 (The Pile)

Max Activating Token Index: 982

Text #4

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.4476. Min Act: -0.0000

Data Index: 1753345 (The Pile)

Max Activating Token Index: 321

Text #5

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.3037. Min Act: -0.0000

Data Index: 319718 (The Pile)

Max Activating Token Index: 976

Text #6

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.3893. Min Act: -0.0000

Data Index: 700691 (The Pile)

Max Activating Token Index: 180

Text #7

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.5847. Min Act: -0.0000

Data Index: 459069 (The Pile)

Max Activating Token Index: 624

Text #8

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.3670. Min Act: -0.0000

Data Index: 1964064 (The Pile)

Max Activating Token Index: 512

Text #9

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.1650. Min Act: -0.0000

Data Index: 1041097 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.2783. Min Act: -0.0000

Data Index: 357203 (The Pile)

Max Activating Token Index: 498

Text #11

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.2201. Min Act: -0.0000

Data Index: 714070 (The Pile)

Max Activating Token Index: 364

Text #12

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.3388. Min Act: -0.0000

Data Index: 1663991 (The Pile)

Max Activating Token Index: 357

Text #13

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.1568. Min Act: -0.0000

Data Index: 1451185 (The Pile)

Max Activating Token Index: 936

Text #14

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.1700. Min Act: -0.0000

Data Index: 739832 (The Pile)

Max Activating Token Index: 702

Text #15

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.0635. Min Act: -0.0000

Data Index: 1077119 (The Pile)

Max Activating Token Index: 585

Text #16

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.1844. Min Act: -0.0000

Data Index: 887076 (The Pile)

Max Activating Token Index: 757

Text #17

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.1065. Min Act: -0.0000

Data Index: 1543399 (The Pile)

Max Activating Token Index: 656

Text #18

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.1878. Min Act: -0.0000

Data Index: 945015 (The Pile)

Max Activating Token Index: 868

Text #19

Max Range: 1.5937. Min Range: -1.5937

Max Act: 1.1546. Min Act: -0.0000

Data Index: 1307687 (The Pile)

Max Activating Token Index: 1012