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

Dataset: The Pile

Neuron 4071 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.3011. Min Act: -0.0000

Data Index: 753973 (The Pile)

Max Activating Token Index: 390

Text #1

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.3421. Min Act: -0.0000

Data Index: 1572724 (The Pile)

Max Activating Token Index: 885

Text #2

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.3536. Min Act: -0.0000

Data Index: 1544126 (The Pile)

Max Activating Token Index: 491

Text #3

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.2926. Min Act: -0.0000

Data Index: 1664365 (The Pile)

Max Activating Token Index: 432

Text #4

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.4090. Min Act: -0.0000

Data Index: 490538 (The Pile)

Max Activating Token Index: 807

Text #5

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.2451. Min Act: -0.0000

Data Index: 1989769 (The Pile)

Max Activating Token Index: 319

Text #6

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.2728. Min Act: -0.0000

Data Index: 1853825 (The Pile)

Max Activating Token Index: 29

Text #7

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.2392. Min Act: -0.0000

Data Index: 1213216 (The Pile)

Max Activating Token Index: 859

Text #8

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.2010. Min Act: -0.0000

Data Index: 335549 (The Pile)

Max Activating Token Index: 274

Text #9

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.1629. Min Act: -0.0000

Data Index: 186537 (The Pile)

Max Activating Token Index: 132

Text #10

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.1674. Min Act: -0.0000

Data Index: 146310 (The Pile)

Max Activating Token Index: 955

Text #11

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.1728. Min Act: -0.0000

Data Index: 1527151 (The Pile)

Max Activating Token Index: 528

Text #12

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.1195. Min Act: -0.0000

Data Index: 1851524 (The Pile)

Max Activating Token Index: 390

Text #13

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.2200. Min Act: -0.0000

Data Index: 1148400 (The Pile)

Max Activating Token Index: 86

Text #14

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.1550. Min Act: -0.0000

Data Index: 1867680 (The Pile)

Max Activating Token Index: 562

Text #15

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.0923. Min Act: -0.0000

Data Index: 403864 (The Pile)

Max Activating Token Index: 188

Text #16

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.1220. Min Act: -0.0000

Data Index: 312407 (The Pile)

Max Activating Token Index: 604

Text #17

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.1469. Min Act: -0.0000

Data Index: 1135721 (The Pile)

Max Activating Token Index: 301

Text #18

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.1785. Min Act: -0.0000

Data Index: 1069462 (The Pile)

Max Activating Token Index: 589

Text #19

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.0789. Min Act: -0.0000

Data Index: 453498 (The Pile)

Max Activating Token Index: 880