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

Dataset: The Pile

Neuron 932 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3227. Min Range: -1.3227

Max Act: 1.3227. Min Act: -0.0000

Data Index: 765322 (The Pile)

Max Activating Token Index: 49

Text #1

Max Range: 1.3227. Min Range: -1.3227

Max Act: 1.1486. Min Act: -0.0000

Data Index: 148492 (The Pile)

Max Activating Token Index: 24

Text #2

Max Range: 1.3227. Min Range: -1.3227

Max Act: 1.0900. Min Act: -0.0000

Data Index: 1020582 (The Pile)

Max Activating Token Index: 160

Text #3

Max Range: 1.3227. Min Range: -1.3227

Max Act: 1.2216. Min Act: -0.0000

Data Index: 1185860 (The Pile)

Max Activating Token Index: 110

Text #4

Max Range: 1.3227. Min Range: -1.3227

Max Act: 1.0577. Min Act: -0.0000

Data Index: 971574 (The Pile)

Max Activating Token Index: 228

Text #5

Max Range: 1.3227. Min Range: -1.3227

Max Act: 1.0734. Min Act: -0.0000

Data Index: 905261 (The Pile)

Max Activating Token Index: 96

Text #6

Max Range: 1.3227. Min Range: -1.3227

Max Act: 1.1278. Min Act: -0.0000

Data Index: 1902613 (The Pile)

Max Activating Token Index: 139

Text #7

Max Range: 1.3227. Min Range: -1.3227

Max Act: 1.0417. Min Act: -0.0000

Data Index: 1462750 (The Pile)

Max Activating Token Index: 685

Text #8

Max Range: 1.3227. Min Range: -1.3227

Max Act: 1.0827. Min Act: -0.0000

Data Index: 1511773 (The Pile)

Max Activating Token Index: 621

Text #9

Max Range: 1.3227. Min Range: -1.3227

Max Act: 1.0316. Min Act: -0.0000

Data Index: 1870781 (The Pile)

Max Activating Token Index: 646

Text #10

Max Range: 1.3227. Min Range: -1.3227

Max Act: 0.8658. Min Act: -0.0000

Data Index: 965892 (The Pile)

Max Activating Token Index: 946

Text #11

Max Range: 1.3227. Min Range: -1.3227

Max Act: 0.8730. Min Act: -0.0000

Data Index: 1539667 (The Pile)

Max Activating Token Index: 449

Text #12

Max Range: 1.3227. Min Range: -1.3227

Max Act: 0.9697. Min Act: -0.0000

Data Index: 1722621 (The Pile)

Max Activating Token Index: 813

Text #13

Max Range: 1.3227. Min Range: -1.3227

Max Act: 1.0044. Min Act: -0.0000

Data Index: 1399579 (The Pile)

Max Activating Token Index: 118

Text #14

Max Range: 1.3227. Min Range: -1.3227

Max Act: 0.9548. Min Act: -0.0000

Data Index: 1557875 (The Pile)

Max Activating Token Index: 880

Text #15

Max Range: 1.3227. Min Range: -1.3227

Max Act: 0.8947. Min Act: -0.0000

Data Index: 1242089 (The Pile)

Max Activating Token Index: 639

Text #16

Max Range: 1.3227. Min Range: -1.3227

Max Act: 0.9768. Min Act: -0.0000

Data Index: 1154518 (The Pile)

Max Activating Token Index: 572

Text #17

Max Range: 1.3227. Min Range: -1.3227

Max Act: 0.9751. Min Act: -0.0000

Data Index: 291649 (The Pile)

Max Activating Token Index: 324

Text #18

Max Range: 1.3227. Min Range: -1.3227

Max Act: 1.0404. Min Act: -0.0000

Data Index: 123884 (The Pile)

Max Activating Token Index: 926

Text #19

Max Range: 1.3227. Min Range: -1.3227

Max Act: 0.9873. Min Act: -0.0000

Data Index: 993032 (The Pile)

Max Activating Token Index: 569