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

Dataset: The Pile

Neuron 4517 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: 1.7912. Min Range: -1.7912

Max Act: 1.7558. Min Act: -0.0000

Data Index: 819125 (The Pile)

Max Activating Token Index: 927

Text #1

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.5964. Min Act: -0.0000

Data Index: 953297 (The Pile)

Max Activating Token Index: 732

Text #2

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.7912. Min Act: -0.0000

Data Index: 667982 (The Pile)

Max Activating Token Index: 327

Text #3

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.7088. Min Act: -0.0000

Data Index: 460173 (The Pile)

Max Activating Token Index: 36

Text #4

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.5475. Min Act: -0.0000

Data Index: 123380 (The Pile)

Max Activating Token Index: 776

Text #5

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.4992. Min Act: -0.0000

Data Index: 400357 (The Pile)

Max Activating Token Index: 199

Text #6

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.5824. Min Act: -0.0000

Data Index: 611311 (The Pile)

Max Activating Token Index: 223

Text #7

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.4942. Min Act: -0.0000

Data Index: 1202615 (The Pile)

Max Activating Token Index: 555

Text #8

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.4903. Min Act: -0.0000

Data Index: 800742 (The Pile)

Max Activating Token Index: 427

Text #9

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.3234. Min Act: -0.0000

Data Index: 994772 (The Pile)

Max Activating Token Index: 166

Text #10

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.3870. Min Act: -0.0000

Data Index: 1349567 (The Pile)

Max Activating Token Index: 737

Text #11

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.2915. Min Act: -0.0000

Data Index: 554299 (The Pile)

Max Activating Token Index: 773

Text #12

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.3771. Min Act: -0.0000

Data Index: 1812223 (The Pile)

Max Activating Token Index: 591

Text #13

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.2782. Min Act: -0.0000

Data Index: 1319026 (The Pile)

Max Activating Token Index: 299

Text #14

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.3729. Min Act: -0.0000

Data Index: 1134210 (The Pile)

Max Activating Token Index: 961

Text #15

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.4313. Min Act: -0.0000

Data Index: 497006 (The Pile)

Max Activating Token Index: 643

Text #16

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.2751. Min Act: -0.0000

Data Index: 1722596 (The Pile)

Max Activating Token Index: 910

Text #17

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.4342. Min Act: -0.0000

Data Index: 46504 (The Pile)

Max Activating Token Index: 121

Text #18

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.4192. Min Act: -0.0000

Data Index: 1686538 (The Pile)

Max Activating Token Index: 855

Text #19

Max Range: 1.7912. Min Range: -1.7912

Max Act: 1.4793. Min Act: -0.0000

Data Index: 241832 (The Pile)

Max Activating Token Index: 911