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

Dataset: The Pile

Neuron 3692 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: 1.1652. Min Range: -1.1652

Max Act: 1.1652. Min Act: -0.0000

Data Index: 578605 (The Pile)

Max Activating Token Index: 245

Text #1

Max Range: 1.1652. Min Range: -1.1652

Max Act: 0.9116. Min Act: -0.0000

Data Index: 1696816 (The Pile)

Max Activating Token Index: 362

Text #2

Max Range: 1.1652. Min Range: -1.1652

Max Act: 0.8665. Min Act: -0.0000

Data Index: 238349 (The Pile)

Max Activating Token Index: 279

Text #3

Max Range: 1.1652. Min Range: -1.1652

Max Act: 0.8234. Min Act: -0.0000

Data Index: 241762 (The Pile)

Max Activating Token Index: 716

Text #4

Max Range: 1.1652. Min Range: -1.1652

Max Act: 0.8195. Min Act: -0.0000

Data Index: 1073495 (The Pile)

Max Activating Token Index: 793

Text #5

Max Range: 1.1652. Min Range: -1.1652

Max Act: 0.8019. Min Act: -0.0000

Data Index: 794620 (The Pile)

Max Activating Token Index: 930

Text #6

Max Range: 1.1652. Min Range: -1.1652

Max Act: 0.7684. Min Act: -0.0000

Data Index: 1062058 (The Pile)

Max Activating Token Index: 480

Text #7

Max Range: 1.1652. Min Range: -1.1652

Max Act: 0.7610. Min Act: -0.0000

Data Index: 512113 (The Pile)

Max Activating Token Index: 774

Text #8

Max Range: 1.1652. Min Range: -1.1652

Max Act: 0.7278. Min Act: -0.0000

Data Index: 1404146 (The Pile)

Max Activating Token Index: 116

Text #9

Max Range: 1.1652. Min Range: -1.1652

Max Act: 0.7243. Min Act: -0.0000

Data Index: 1787533 (The Pile)

Max Activating Token Index: 156

Text #10

Max Range: 1.1652. Min Range: -1.1652

Max Act: 0.6522. Min Act: -0.0000

Data Index: 1659405 (The Pile)

Max Activating Token Index: 641

Text #11

Max Range: 1.1652. Min Range: -1.1652

Max Act: 0.7405. Min Act: -0.0000

Data Index: 1150090 (The Pile)

Max Activating Token Index: 202

Text #12

Max Range: 1.1652. Min Range: -1.1652

Max Act: 0.7332. Min Act: -0.0000

Data Index: 137195 (The Pile)

Max Activating Token Index: 594

Text #13

Max Range: 1.1652. Min Range: -1.1652

Max Act: 0.7322. Min Act: -0.0000

Data Index: 38539 (The Pile)

Max Activating Token Index: 1005

Text #14

Max Range: 1.1652. Min Range: -1.1652

Max Act: 0.7052. Min Act: -0.0000

Data Index: 623752 (The Pile)

Max Activating Token Index: 259

Text #15

Max Range: 1.1652. Min Range: -1.1652

Max Act: 0.7256. Min Act: -0.0000

Data Index: 565577 (The Pile)

Max Activating Token Index: 172

Text #16

Max Range: 1.1652. Min Range: -1.1652

Max Act: 0.7676. Min Act: -0.0000

Data Index: 1445565 (The Pile)

Max Activating Token Index: 98

Text #17

Max Range: 1.1652. Min Range: -1.1652

Max Act: 0.7024. Min Act: -0.0000

Data Index: 514067 (The Pile)

Max Activating Token Index: 561

Text #18

Max Range: 1.1652. Min Range: -1.1652

Max Act: 0.6941. Min Act: -0.0000

Data Index: 1452073 (The Pile)

Max Activating Token Index: 286

Text #19

Max Range: 1.1652. Min Range: -1.1652

Max Act: 0.6929. Min Act: -0.0000

Data Index: 1648345 (The Pile)

Max Activating Token Index: 553