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

Dataset: The Pile

Neuron 4481 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: 1.0761. Min Range: -1.0761

Max Act: 1.0761. Min Act: -0.0000

Data Index: 1316884 (The Pile)

Max Activating Token Index: 910

Text #1

Max Range: 1.0761. Min Range: -1.0761

Max Act: 0.8993. Min Act: -0.0000

Data Index: 224523 (The Pile)

Max Activating Token Index: 193

Text #2

Max Range: 1.0761. Min Range: -1.0761

Max Act: 0.9641. Min Act: -0.0000

Data Index: 569572 (The Pile)

Max Activating Token Index: 695

Text #3

Max Range: 1.0761. Min Range: -1.0761

Max Act: 0.7836. Min Act: -0.0000

Data Index: 630060 (The Pile)

Max Activating Token Index: 682

Text #4

Max Range: 1.0761. Min Range: -1.0761

Max Act: 0.7034. Min Act: -0.0000

Data Index: 214981 (The Pile)

Max Activating Token Index: 46

Text #5

Max Range: 1.0761. Min Range: -1.0761

Max Act: 0.7449. Min Act: -0.0000

Data Index: 1659299 (The Pile)

Max Activating Token Index: 488

Text #6

Max Range: 1.0761. Min Range: -1.0761

Max Act: 0.6967. Min Act: -0.0000

Data Index: 1238984 (The Pile)

Max Activating Token Index: 421

Text #7

Max Range: 1.0761. Min Range: -1.0761

Max Act: 0.7105. Min Act: -0.0000

Data Index: 1903719 (The Pile)

Max Activating Token Index: 435

Text #8

Max Range: 1.0761. Min Range: -1.0761

Max Act: 0.7556. Min Act: -0.0000

Data Index: 1972418 (The Pile)

Max Activating Token Index: 159

Text #9

Max Range: 1.0761. Min Range: -1.0761

Max Act: 0.7200. Min Act: -0.0000

Data Index: 193254 (The Pile)

Max Activating Token Index: 1010

Text #10

Max Range: 1.0761. Min Range: -1.0761

Max Act: 0.7227. Min Act: -0.0000

Data Index: 1881456 (The Pile)

Max Activating Token Index: 350

Text #11

Max Range: 1.0761. Min Range: -1.0761

Max Act: 0.6958. Min Act: -0.0000

Data Index: 733288 (The Pile)

Max Activating Token Index: 845

Text #12

Max Range: 1.0761. Min Range: -1.0761

Max Act: 0.7057. Min Act: -0.0000

Data Index: 1807498 (The Pile)

Max Activating Token Index: 548

Text #13

Max Range: 1.0761. Min Range: -1.0761

Max Act: 0.6843. Min Act: -0.0000

Data Index: 1225790 (The Pile)

Max Activating Token Index: 342

Text #14

Max Range: 1.0761. Min Range: -1.0761

Max Act: 0.6742. Min Act: -0.0000

Data Index: 710825 (The Pile)

Max Activating Token Index: 320

Text #15

Max Range: 1.0761. Min Range: -1.0761

Max Act: 0.6710. Min Act: -0.0000

Data Index: 1652389 (The Pile)

Max Activating Token Index: 82

Text #16

Max Range: 1.0761. Min Range: -1.0761

Max Act: 0.7910. Min Act: -0.0000

Data Index: 528195 (The Pile)

Max Activating Token Index: 998

Text #17

Max Range: 1.0761. Min Range: -1.0761

Max Act: 0.7088. Min Act: -0.0000

Data Index: 1455134 (The Pile)

Max Activating Token Index: 862

Text #18

Max Range: 1.0761. Min Range: -1.0761

Max Act: 0.7695. Min Act: -0.0000

Data Index: 85170 (The Pile)

Max Activating Token Index: 671

Text #19

Max Range: 1.0761. Min Range: -1.0761

Max Act: 0.6773. Min Act: -0.0000

Data Index: 1982832 (The Pile)

Max Activating Token Index: 529