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

Dataset: The Pile

Neuron 3448 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9637. Min Range: -5.9637

Max Act: 5.9637. Min Act: -0.0000

Data Index: 360184 (The Pile)

Max Activating Token Index: 378

Text #1

Max Range: 5.9637. Min Range: -5.9637

Max Act: 5.6235. Min Act: -0.0000

Data Index: 1032609 (The Pile)

Max Activating Token Index: 945

Text #2

Max Range: 5.9637. Min Range: -5.9637

Max Act: 5.4442. Min Act: -0.0000

Data Index: 1511618 (The Pile)

Max Activating Token Index: 852

Text #3

Max Range: 5.9637. Min Range: -5.9637

Max Act: 5.4205. Min Act: 0.0000

Data Index: 281059 (The Pile)

Max Activating Token Index: 655

Text #4

Max Range: 5.9637. Min Range: -5.9637

Max Act: 5.7896. Min Act: -0.0000

Data Index: 1891048 (The Pile)

Max Activating Token Index: 417

Text #5

Max Range: 5.9637. Min Range: -5.9637

Max Act: 5.0551. Min Act: -0.0000

Data Index: 309867 (The Pile)

Max Activating Token Index: 695

Text #6

Max Range: 5.9637. Min Range: -5.9637

Max Act: 5.0027. Min Act: -0.0000

Data Index: 403240 (The Pile)

Max Activating Token Index: 783

Text #7

Max Range: 5.9637. Min Range: -5.9637

Max Act: 4.9269. Min Act: -0.0000

Data Index: 980458 (The Pile)

Max Activating Token Index: 657

Text #8

Max Range: 5.9637. Min Range: -5.9637

Max Act: 5.2463. Min Act: -0.0000

Data Index: 1927865 (The Pile)

Max Activating Token Index: 312

Text #9

Max Range: 5.9637. Min Range: -5.9637

Max Act: 5.0879. Min Act: -0.0000

Data Index: 1279514 (The Pile)

Max Activating Token Index: 182

Text #10

Max Range: 5.9637. Min Range: -5.9637

Max Act: 4.5030. Min Act: -0.0000

Data Index: 1670066 (The Pile)

Max Activating Token Index: 784

Text #11

Max Range: 5.9637. Min Range: -5.9637

Max Act: 4.6996. Min Act: -0.0000

Data Index: 1055088 (The Pile)

Max Activating Token Index: 185

Text #12

Max Range: 5.9637. Min Range: -5.9637

Max Act: 4.7833. Min Act: 0.0000

Data Index: 1684873 (The Pile)

Max Activating Token Index: 454

Text #13

Max Range: 5.9637. Min Range: -5.9637

Max Act: 4.7482. Min Act: -0.0000

Data Index: 70725 (The Pile)

Max Activating Token Index: 549

Text #14

Max Range: 5.9637. Min Range: -5.9637

Max Act: 5.1307. Min Act: 0.0000

Data Index: 1727338 (The Pile)

Max Activating Token Index: 96

Text #15

Max Range: 5.9637. Min Range: -5.9637

Max Act: 4.8690. Min Act: 0.0000

Data Index: 805334 (The Pile)

Max Activating Token Index: 615

Text #16

Max Range: 5.9637. Min Range: -5.9637

Max Act: 4.6676. Min Act: -0.0000

Data Index: 1908625 (The Pile)

Max Activating Token Index: 184

Text #17

Max Range: 5.9637. Min Range: -5.9637

Max Act: 4.4964. Min Act: -0.0000

Data Index: 1605882 (The Pile)

Max Activating Token Index: 53

Text #18

Max Range: 5.9637. Min Range: -5.9637

Max Act: 4.6789. Min Act: -0.0000

Data Index: 402148 (The Pile)

Max Activating Token Index: 508

Text #19

Max Range: 5.9637. Min Range: -5.9637

Max Act: 4.6577. Min Act: -0.0000

Data Index: 133080 (The Pile)

Max Activating Token Index: 591