Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2937 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.2077. Min Act: -0.0000

Data Index: 694536 (The Pile)

Max Activating Token Index: 465

Text #1

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1982. Min Act: -0.0000

Data Index: 1210917 (The Pile)

Max Activating Token Index: 379

Text #2

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1926. Min Act: -0.0000

Data Index: 237814 (The Pile)

Max Activating Token Index: 39

Text #3

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1985. Min Act: -0.0000

Data Index: 607375 (The Pile)

Max Activating Token Index: 883

Text #4

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1908. Min Act: -0.0000

Data Index: 609892 (The Pile)

Max Activating Token Index: 1002

Text #5

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1900. Min Act: -0.0000

Data Index: 897559 (The Pile)

Max Activating Token Index: 534

Text #6

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1835. Min Act: -0.0000

Data Index: 829126 (The Pile)

Max Activating Token Index: 715

Text #7

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1798. Min Act: -0.0000

Data Index: 286195 (The Pile)

Max Activating Token Index: 828

Text #8

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1747. Min Act: -0.0000

Data Index: 87936 (The Pile)

Max Activating Token Index: 45

Text #9

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1710. Min Act: -0.0000

Data Index: 1612864 (The Pile)

Max Activating Token Index: 527

Text #10

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1744. Min Act: -0.0000

Data Index: 1770210 (The Pile)

Max Activating Token Index: 330

Text #11

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1670. Min Act: -0.0000

Data Index: 1638567 (The Pile)

Max Activating Token Index: 931

Text #12

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1730. Min Act: -0.0000

Data Index: 1878677 (The Pile)

Max Activating Token Index: 149

Text #13

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1615. Min Act: -0.0000

Data Index: 1603999 (The Pile)

Max Activating Token Index: 127

Text #14

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1724. Min Act: -0.0000

Data Index: 1113752 (The Pile)

Max Activating Token Index: 362

Text #15

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1695. Min Act: -0.0000

Data Index: 73575 (The Pile)

Max Activating Token Index: 902

Text #16

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1585. Min Act: -0.0000

Data Index: 1704346 (The Pile)

Max Activating Token Index: 327

Text #17

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1589. Min Act: -0.0000

Data Index: 1412550 (The Pile)

Max Activating Token Index: 970

Text #18

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1583. Min Act: -0.0000

Data Index: 1931314 (The Pile)

Max Activating Token Index: 927

Text #19

Max Range: 0.2077. Min Range: -0.2077

Max Act: 0.1624. Min Act: -0.0000

Data Index: 641125 (The Pile)

Max Activating Token Index: 455