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

Dataset: The Pile

Neuron 1414 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: 1.2767. Min Range: -1.2767

Max Act: 1.2767. Min Act: -0.0000

Data Index: 1380613 (The Pile)

Max Activating Token Index: 782

Text #1

Max Range: 1.2767. Min Range: -1.2767

Max Act: 1.1694. Min Act: -0.0000

Data Index: 1456765 (The Pile)

Max Activating Token Index: 918

Text #2

Max Range: 1.2767. Min Range: -1.2767

Max Act: 1.0783. Min Act: -0.0000

Data Index: 950105 (The Pile)

Max Activating Token Index: 927

Text #3

Max Range: 1.2767. Min Range: -1.2767

Max Act: 1.1448. Min Act: -0.0000

Data Index: 1722505 (The Pile)

Max Activating Token Index: 380

Text #4

Max Range: 1.2767. Min Range: -1.2767

Max Act: 1.0648. Min Act: -0.0000

Data Index: 729090 (The Pile)

Max Activating Token Index: 182

Text #5

Max Range: 1.2767. Min Range: -1.2767

Max Act: 1.0475. Min Act: -0.0000

Data Index: 183623 (The Pile)

Max Activating Token Index: 152

Text #6

Max Range: 1.2767. Min Range: -1.2767

Max Act: 1.0745. Min Act: -0.0000

Data Index: 231602 (The Pile)

Max Activating Token Index: 838

Text #7

Max Range: 1.2767. Min Range: -1.2767

Max Act: 1.0850. Min Act: -0.0000

Data Index: 1870940 (The Pile)

Max Activating Token Index: 470

Text #8

Max Range: 1.2767. Min Range: -1.2767

Max Act: 0.9577. Min Act: -0.0000

Data Index: 204183 (The Pile)

Max Activating Token Index: 1019

Text #9

Max Range: 1.2767. Min Range: -1.2767

Max Act: 1.0576. Min Act: -0.0000

Data Index: 607409 (The Pile)

Max Activating Token Index: 733

Text #10

Max Range: 1.2767. Min Range: -1.2767

Max Act: 1.0557. Min Act: -0.0000

Data Index: 516212 (The Pile)

Max Activating Token Index: 865

Text #11

Max Range: 1.2767. Min Range: -1.2767

Max Act: 1.1469. Min Act: -0.0000

Data Index: 1453927 (The Pile)

Max Activating Token Index: 989

Text #12

Max Range: 1.2767. Min Range: -1.2767

Max Act: 1.0237. Min Act: -0.0000

Data Index: 630439 (The Pile)

Max Activating Token Index: 435

Text #13

Max Range: 1.2767. Min Range: -1.2767

Max Act: 1.0565. Min Act: -0.0000

Data Index: 423471 (The Pile)

Max Activating Token Index: 612

Text #14

Max Range: 1.2767. Min Range: -1.2767

Max Act: 0.9694. Min Act: -0.0000

Data Index: 1433617 (The Pile)

Max Activating Token Index: 550

Text #15

Max Range: 1.2767. Min Range: -1.2767

Max Act: 1.1809. Min Act: -0.0000

Data Index: 1048733 (The Pile)

Max Activating Token Index: 899

Text #16

Max Range: 1.2767. Min Range: -1.2767

Max Act: 0.9489. Min Act: -0.0000

Data Index: 1844111 (The Pile)

Max Activating Token Index: 850

Text #17

Max Range: 1.2767. Min Range: -1.2767

Max Act: 1.0322. Min Act: -0.0000

Data Index: 848001 (The Pile)

Max Activating Token Index: 941

Text #18

Max Range: 1.2767. Min Range: -1.2767

Max Act: 0.9920. Min Act: -0.0000

Data Index: 626371 (The Pile)

Max Activating Token Index: 199

Text #19

Max Range: 1.2767. Min Range: -1.2767

Max Act: 0.9130. Min Act: -0.0000

Data Index: 656670 (The Pile)

Max Activating Token Index: 937