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

Dataset: The Pile

Neuron 1918 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: 0.2062. Min Range: -0.2062

Max Act: 0.2062. Min Act: -0.0000

Data Index: 1570633 (The Pile)

Max Activating Token Index: 700

Text #1

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1967. Min Act: -0.0000

Data Index: 337127 (The Pile)

Max Activating Token Index: 318

Text #2

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1766. Min Act: -0.0000

Data Index: 53457 (The Pile)

Max Activating Token Index: 329

Text #3

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1953. Min Act: -0.0000

Data Index: 1206897 (The Pile)

Max Activating Token Index: 581

Text #4

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1847. Min Act: -0.0000

Data Index: 906595 (The Pile)

Max Activating Token Index: 142

Text #5

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1834. Min Act: -0.0000

Data Index: 648744 (The Pile)

Max Activating Token Index: 651

Text #6

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1876. Min Act: -0.0000

Data Index: 190581 (The Pile)

Max Activating Token Index: 782

Text #7

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1938. Min Act: -0.0000

Data Index: 1265286 (The Pile)

Max Activating Token Index: 1007

Text #8

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1665. Min Act: -0.0000

Data Index: 1574531 (The Pile)

Max Activating Token Index: 106

Text #9

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1770. Min Act: -0.0000

Data Index: 1024188 (The Pile)

Max Activating Token Index: 253

Text #10

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1635. Min Act: -0.0000

Data Index: 1281829 (The Pile)

Max Activating Token Index: 398

Text #11

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1701. Min Act: -0.0000

Data Index: 485308 (The Pile)

Max Activating Token Index: 543

Text #12

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1629. Min Act: -0.0001

Data Index: 217468 (The Pile)

Max Activating Token Index: 1021

Text #13

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1623. Min Act: -0.0000

Data Index: 1683979 (The Pile)

Max Activating Token Index: 343

Text #14

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1717. Min Act: -0.0000

Data Index: 1118432 (The Pile)

Max Activating Token Index: 602

Text #15

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1592. Min Act: -0.0000

Data Index: 1680310 (The Pile)

Max Activating Token Index: 711

Text #16

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1702. Min Act: -0.0000

Data Index: 1505938 (The Pile)

Max Activating Token Index: 900

Text #17

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1623. Min Act: -0.0000

Data Index: 339525 (The Pile)

Max Activating Token Index: 655

Text #18

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1516. Min Act: -0.0000

Data Index: 978170 (The Pile)

Max Activating Token Index: 491

Text #19

Max Range: 0.2062. Min Range: -0.2062

Max Act: 0.1461. Min Act: -0.0000

Data Index: 460582 (The Pile)

Max Activating Token Index: 571