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

Dataset: The Pile

Neuron 753 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.8773. Min Act: -0.0000

Data Index: 1511477 (The Pile)

Max Activating Token Index: 426

Text #1

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.4174. Min Act: -0.0000

Data Index: 1772422 (The Pile)

Max Activating Token Index: 1003

Text #2

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.5802. Min Act: -0.0000

Data Index: 72506 (The Pile)

Max Activating Token Index: 910

Text #3

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.4327. Min Act: 0.0000

Data Index: 1966912 (The Pile)

Max Activating Token Index: 507

Text #4

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.4007. Min Act: -0.0000

Data Index: 1294407 (The Pile)

Max Activating Token Index: 448

Text #5

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.2936. Min Act: -0.0000

Data Index: 1534187 (The Pile)

Max Activating Token Index: 156

Text #6

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.2783. Min Act: -0.0000

Data Index: 1007524 (The Pile)

Max Activating Token Index: 734

Text #7

Max Range: 1.8773. Min Range: -1.8773

Max Act: 1.0434. Min Act: -0.0000

Data Index: 1782337 (The Pile)

Max Activating Token Index: 995

Text #8

Max Range: 1.8773. Min Range: -1.8773

Max Act: 0.8962. Min Act: -0.0000

Data Index: 688879 (The Pile)

Max Activating Token Index: 992

Text #9

Max Range: 1.8773. Min Range: -1.8773

Max Act: 0.9561. Min Act: -0.0000

Data Index: 1480943 (The Pile)

Max Activating Token Index: 1001

Text #10

Max Range: 1.8773. Min Range: -1.8773

Max Act: 0.9306. Min Act: -0.0000

Data Index: 1365936 (The Pile)

Max Activating Token Index: 922

Text #11

Max Range: 1.8773. Min Range: -1.8773

Max Act: 0.9124. Min Act: 0.0000

Data Index: 548820 (The Pile)

Max Activating Token Index: 307

Text #12

Max Range: 1.8773. Min Range: -1.8773

Max Act: 0.7298. Min Act: -0.0000

Data Index: 664141 (The Pile)

Max Activating Token Index: 969

Text #13

Max Range: 1.8773. Min Range: -1.8773

Max Act: 0.8581. Min Act: -0.0000

Data Index: 1799459 (The Pile)

Max Activating Token Index: 112

Text #14

Max Range: 1.8773. Min Range: -1.8773

Max Act: 0.7959. Min Act: -0.0000

Data Index: 1383638 (The Pile)

Max Activating Token Index: 583

Text #15

Max Range: 1.8773. Min Range: -1.8773

Max Act: 0.8575. Min Act: -0.0000

Data Index: 1717202 (The Pile)

Max Activating Token Index: 36

Text #16

Max Range: 1.8773. Min Range: -1.8773

Max Act: 0.7531. Min Act: -0.0000

Data Index: 1614683 (The Pile)

Max Activating Token Index: 369

Text #17

Max Range: 1.8773. Min Range: -1.8773

Max Act: 0.8355. Min Act: -0.0000

Data Index: 1625198 (The Pile)

Max Activating Token Index: 718

Text #18

Max Range: 1.8773. Min Range: -1.8773

Max Act: 0.8180. Min Act: -0.0000

Data Index: 703177 (The Pile)

Max Activating Token Index: 93

Text #19

Max Range: 1.8773. Min Range: -1.8773

Max Act: 0.7841. Min Act: -0.0000

Data Index: 132782 (The Pile)

Max Activating Token Index: 32