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

Dataset: The Pile

Neuron 1711 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: 0.3151. Min Range: -0.3151

Max Act: 0.3151. Min Act: -0.0000

Data Index: 1434964 (The Pile)

Max Activating Token Index: 355

Text #1

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.2225. Min Act: -0.0000

Data Index: 857339 (The Pile)

Max Activating Token Index: 895

Text #2

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.2269. Min Act: -0.0000

Data Index: 962438 (The Pile)

Max Activating Token Index: 582

Text #3

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.1848. Min Act: -0.0000

Data Index: 1360851 (The Pile)

Max Activating Token Index: 572

Text #4

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.1949. Min Act: -0.0000

Data Index: 239140 (The Pile)

Max Activating Token Index: 615

Text #5

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.1879. Min Act: -0.0000

Data Index: 1549872 (The Pile)

Max Activating Token Index: 909

Text #6

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.1897. Min Act: -0.0000

Data Index: 689076 (The Pile)

Max Activating Token Index: 363

Text #7

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.1938. Min Act: -0.0000

Data Index: 263082 (The Pile)

Max Activating Token Index: 715

Text #8

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.1829. Min Act: -0.0000

Data Index: 579987 (The Pile)

Max Activating Token Index: 439

Text #9

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.1761. Min Act: -0.0000

Data Index: 725202 (The Pile)

Max Activating Token Index: 933

Text #10

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.1622. Min Act: -0.0000

Data Index: 457175 (The Pile)

Max Activating Token Index: 709

Text #11

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.1747. Min Act: -0.0000

Data Index: 1140717 (The Pile)

Max Activating Token Index: 817

Text #12

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.1738. Min Act: -0.0000

Data Index: 946706 (The Pile)

Max Activating Token Index: 785

Text #13

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.1670. Min Act: -0.0000

Data Index: 920799 (The Pile)

Max Activating Token Index: 733

Text #14

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.1806. Min Act: -0.0000

Data Index: 142299 (The Pile)

Max Activating Token Index: 919

Text #15

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.1750. Min Act: -0.0000

Data Index: 891983 (The Pile)

Max Activating Token Index: 517

Text #16

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.1725. Min Act: -0.0000

Data Index: 1840040 (The Pile)

Max Activating Token Index: 827

Text #17

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.1749. Min Act: -0.0000

Data Index: 1040852 (The Pile)

Max Activating Token Index: 759

Text #18

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.1689. Min Act: -0.0000

Data Index: 414063 (The Pile)

Max Activating Token Index: 871

Text #19

Max Range: 0.3151. Min Range: -0.3151

Max Act: 0.1637. Min Act: -0.0000

Data Index: 987083 (The Pile)

Max Activating Token Index: 654