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

Dataset: The Pile

Neuron 671 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: 0.5218. Min Range: -0.5218

Max Act: 0.5218. Min Act: -0.0000

Data Index: 1818969 (The Pile)

Max Activating Token Index: 911

Text #1

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.5131. Min Act: -0.0000

Data Index: 1931511 (The Pile)

Max Activating Token Index: 756

Text #2

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4351. Min Act: -0.0000

Data Index: 447580 (The Pile)

Max Activating Token Index: 652

Text #3

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4386. Min Act: -0.0000

Data Index: 237204 (The Pile)

Max Activating Token Index: 434

Text #4

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4500. Min Act: -0.0000

Data Index: 513233 (The Pile)

Max Activating Token Index: 485

Text #5

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4587. Min Act: -0.0000

Data Index: 955278 (The Pile)

Max Activating Token Index: 424

Text #6

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4442. Min Act: -0.0000

Data Index: 1376590 (The Pile)

Max Activating Token Index: 768

Text #7

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4242. Min Act: -0.0000

Data Index: 126879 (The Pile)

Max Activating Token Index: 247

Text #8

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4485. Min Act: -0.0000

Data Index: 97805 (The Pile)

Max Activating Token Index: 120

Text #9

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4155. Min Act: -0.0000

Data Index: 1772796 (The Pile)

Max Activating Token Index: 551

Text #10

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4137. Min Act: -0.0000

Data Index: 244386 (The Pile)

Max Activating Token Index: 276

Text #11

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.3856. Min Act: -0.0000

Data Index: 1950250 (The Pile)

Max Activating Token Index: 891

Text #12

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.3967. Min Act: -0.0000

Data Index: 1086371 (The Pile)

Max Activating Token Index: 722

Text #13

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4118. Min Act: -0.0000

Data Index: 1494626 (The Pile)

Max Activating Token Index: 316

Text #14

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4240. Min Act: -0.0000

Data Index: 1082514 (The Pile)

Max Activating Token Index: 383

Text #15

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.3823. Min Act: -0.0000

Data Index: 278200 (The Pile)

Max Activating Token Index: 464

Text #16

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.3934. Min Act: -0.0000

Data Index: 841231 (The Pile)

Max Activating Token Index: 769

Text #17

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.4171. Min Act: -0.0000

Data Index: 862208 (The Pile)

Max Activating Token Index: 481

Text #18

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.3779. Min Act: -0.0000

Data Index: 1352274 (The Pile)

Max Activating Token Index: 599

Text #19

Max Range: 0.5218. Min Range: -0.5218

Max Act: 0.3899. Min Act: -0.0000

Data Index: 1526986 (The Pile)

Max Activating Token Index: 560