Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 4068 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.3606. Min Act: -0.0000

Data Index: 496167 (The Pile)

Max Activating Token Index: 800

Text #1

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.3646. Min Act: -0.0000

Data Index: 837768 (The Pile)

Max Activating Token Index: 664

Text #2

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.2598. Min Act: -0.0000

Data Index: 1990067 (The Pile)

Max Activating Token Index: 986

Text #3

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.1928. Min Act: -0.0000

Data Index: 866540 (The Pile)

Max Activating Token Index: 165

Text #4

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.1607. Min Act: -0.0000

Data Index: 1465001 (The Pile)

Max Activating Token Index: 749

Text #5

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.1733. Min Act: -0.0000

Data Index: 430016 (The Pile)

Max Activating Token Index: 146

Text #6

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.0601. Min Act: -0.0000

Data Index: 1440163 (The Pile)

Max Activating Token Index: 464

Text #7

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.1068. Min Act: -0.0000

Data Index: 1029780 (The Pile)

Max Activating Token Index: 97

Text #8

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.1710. Min Act: -0.0000

Data Index: 1388066 (The Pile)

Max Activating Token Index: 957

Text #9

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.0973. Min Act: -0.0000

Data Index: 1707901 (The Pile)

Max Activating Token Index: 108

Text #10

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.0311. Min Act: -0.0000

Data Index: 1382879 (The Pile)

Max Activating Token Index: 1020

Text #11

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.1224. Min Act: -0.0000

Data Index: 1151550 (The Pile)

Max Activating Token Index: 593

Text #12

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.0071. Min Act: -0.0000

Data Index: 1115549 (The Pile)

Max Activating Token Index: 409

Text #13

Max Range: 1.3646. Min Range: -1.3646

Max Act: 0.9453. Min Act: -0.0000

Data Index: 1627447 (The Pile)

Max Activating Token Index: 717

Text #14

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.0914. Min Act: -0.0000

Data Index: 570664 (The Pile)

Max Activating Token Index: 973

Text #15

Max Range: 1.3646. Min Range: -1.3646

Max Act: 1.0572. Min Act: -0.0000

Data Index: 696848 (The Pile)

Max Activating Token Index: 968

Text #16

Max Range: 1.3646. Min Range: -1.3646

Max Act: 0.9477. Min Act: -0.0000

Data Index: 276172 (The Pile)

Max Activating Token Index: 591

Text #17

Max Range: 1.3646. Min Range: -1.3646

Max Act: 0.9230. Min Act: -0.0000

Data Index: 1868096 (The Pile)

Max Activating Token Index: 510

Text #18

Max Range: 1.3646. Min Range: -1.3646

Max Act: 0.9788. Min Act: -0.0000

Data Index: 894896 (The Pile)

Max Activating Token Index: 251

Text #19

Max Range: 1.3646. Min Range: -1.3646

Max Act: 0.9939. Min Act: -0.0000

Data Index: 177864 (The Pile)

Max Activating Token Index: 749