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

Dataset: The Pile

Neuron 5105 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: 0.1799. Min Range: -0.1799

Max Act: 0.1799. Min Act: -0.0000

Data Index: 997714 (The Pile)

Max Activating Token Index: 548

Text #1

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1412. Min Act: -0.0000

Data Index: 1762291 (The Pile)

Max Activating Token Index: 735

Text #2

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1167. Min Act: -0.0000

Data Index: 953160 (The Pile)

Max Activating Token Index: 795

Text #3

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1160. Min Act: -0.0000

Data Index: 1023927 (The Pile)

Max Activating Token Index: 629

Text #4

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1231. Min Act: -0.0000

Data Index: 1532283 (The Pile)

Max Activating Token Index: 570

Text #5

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1205. Min Act: -0.0000

Data Index: 1248517 (The Pile)

Max Activating Token Index: 516

Text #6

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1209. Min Act: -0.0000

Data Index: 198246 (The Pile)

Max Activating Token Index: 341

Text #7

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1263. Min Act: -0.0000

Data Index: 1740934 (The Pile)

Max Activating Token Index: 883

Text #8

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.1170. Min Act: -0.0000

Data Index: 1926180 (The Pile)

Max Activating Token Index: 718

Text #9

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.0797. Min Act: -0.0000

Data Index: 1727608 (The Pile)

Max Activating Token Index: 1022

Text #10

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.0836. Min Act: -0.0000

Data Index: 1112839 (The Pile)

Max Activating Token Index: 670

Text #11

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.0856. Min Act: -0.0000

Data Index: 129884 (The Pile)

Max Activating Token Index: 919

Text #12

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.0860. Min Act: -0.0000

Data Index: 1569471 (The Pile)

Max Activating Token Index: 766

Text #13

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.0957. Min Act: -0.0000

Data Index: 611275 (The Pile)

Max Activating Token Index: 967

Text #14

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.0841. Min Act: -0.0000

Data Index: 171571 (The Pile)

Max Activating Token Index: 753

Text #15

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.0847. Min Act: -0.0000

Data Index: 468264 (The Pile)

Max Activating Token Index: 972

Text #16

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.0749. Min Act: -0.0000

Data Index: 1680278 (The Pile)

Max Activating Token Index: 674

Text #17

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.0739. Min Act: -0.0000

Data Index: 769299 (The Pile)

Max Activating Token Index: 672

Text #18

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.0697. Min Act: -0.0000

Data Index: 719139 (The Pile)

Max Activating Token Index: 746

Text #19

Max Range: 0.1799. Min Range: -0.1799

Max Act: 0.0644. Min Act: -0.0000

Data Index: 645661 (The Pile)

Max Activating Token Index: 887