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

Dataset: The Pile

Neuron 592 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2708. Min Act: -0.0000

Data Index: 1646539 (The Pile)

Max Activating Token Index: 674

Text #1

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2430. Min Act: -0.0000

Data Index: 1571751 (The Pile)

Max Activating Token Index: 738

Text #2

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2437. Min Act: -0.0000

Data Index: 1012487 (The Pile)

Max Activating Token Index: 480

Text #3

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2577. Min Act: -0.0000

Data Index: 1823234 (The Pile)

Max Activating Token Index: 976

Text #4

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2208. Min Act: -0.0000

Data Index: 1228164 (The Pile)

Max Activating Token Index: 707

Text #5

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2210. Min Act: -0.0000

Data Index: 598215 (The Pile)

Max Activating Token Index: 683

Text #6

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2251. Min Act: -0.0000

Data Index: 1631282 (The Pile)

Max Activating Token Index: 901

Text #7

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2241. Min Act: -0.0000

Data Index: 1183664 (The Pile)

Max Activating Token Index: 988

Text #8

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2155. Min Act: -0.0000

Data Index: 1694977 (The Pile)

Max Activating Token Index: 715

Text #9

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.1918. Min Act: -0.0000

Data Index: 937576 (The Pile)

Max Activating Token Index: 353

Text #10

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.1905. Min Act: -0.0000

Data Index: 1181036 (The Pile)

Max Activating Token Index: 376

Text #11

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.1893. Min Act: -0.0000

Data Index: 882624 (The Pile)

Max Activating Token Index: 854

Text #12

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.1698. Min Act: -0.0000

Data Index: 1021256 (The Pile)

Max Activating Token Index: 1004

Text #13

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.1784. Min Act: -0.0000

Data Index: 782875 (The Pile)

Max Activating Token Index: 907

Text #14

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.1917. Min Act: -0.0000

Data Index: 210143 (The Pile)

Max Activating Token Index: 834

Text #15

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2019. Min Act: 0.0000

Data Index: 1004445 (The Pile)

Max Activating Token Index: 973

Text #16

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.2029. Min Act: -0.0000

Data Index: 1655138 (The Pile)

Max Activating Token Index: 890

Text #17

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.1842. Min Act: 0.0000

Data Index: 277225 (The Pile)

Max Activating Token Index: 896

Text #18

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.1764. Min Act: -0.0000

Data Index: 1251659 (The Pile)

Max Activating Token Index: 953

Text #19

Max Range: 0.2708. Min Range: -0.2708

Max Act: 0.1846. Min Act: -0.0000

Data Index: 257337 (The Pile)

Max Activating Token Index: 720