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

Dataset: The Pile

Neuron 2438 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.6119. Min Act: -0.0000

Data Index: 207434 (The Pile)

Max Activating Token Index: 748

Text #1

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.3837. Min Act: -0.0000

Data Index: 263676 (The Pile)

Max Activating Token Index: 746

Text #2

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.2689. Min Act: -0.0000

Data Index: 1759005 (The Pile)

Max Activating Token Index: 683

Text #3

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.1829. Min Act: -0.0000

Data Index: 1804571 (The Pile)

Max Activating Token Index: 359

Text #4

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.2312. Min Act: -0.0000

Data Index: 1664095 (The Pile)

Max Activating Token Index: 990

Text #5

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.2208. Min Act: -0.0000

Data Index: 867178 (The Pile)

Max Activating Token Index: 76

Text #6

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.2117. Min Act: -0.0000

Data Index: 1774865 (The Pile)

Max Activating Token Index: 862

Text #7

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.2002. Min Act: -0.0000

Data Index: 297881 (The Pile)

Max Activating Token Index: 722

Text #8

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.1939. Min Act: -0.0000

Data Index: 1905373 (The Pile)

Max Activating Token Index: 563

Text #9

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.2272. Min Act: -0.0000

Data Index: 1839856 (The Pile)

Max Activating Token Index: 149

Text #10

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.0856. Min Act: -0.0000

Data Index: 333757 (The Pile)

Max Activating Token Index: 103

Text #11

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.1486. Min Act: -0.0000

Data Index: 131880 (The Pile)

Max Activating Token Index: 825

Text #12

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.1377. Min Act: -0.0000

Data Index: 1058091 (The Pile)

Max Activating Token Index: 808

Text #13

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.2154. Min Act: -0.0000

Data Index: 1674155 (The Pile)

Max Activating Token Index: 613

Text #14

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.1239. Min Act: -0.0000

Data Index: 1034757 (The Pile)

Max Activating Token Index: 559

Text #15

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.1289. Min Act: -0.0000

Data Index: 883924 (The Pile)

Max Activating Token Index: 525

Text #16

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.1300. Min Act: -0.0000

Data Index: 296026 (The Pile)

Max Activating Token Index: 685

Text #17

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.0598. Min Act: -0.0000

Data Index: 734544 (The Pile)

Max Activating Token Index: 103

Text #18

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.1155. Min Act: -0.0000

Data Index: 1382512 (The Pile)

Max Activating Token Index: 325

Text #19

Max Range: 1.6119. Min Range: -1.6119

Max Act: 1.1217. Min Act: -0.0000

Data Index: 1365784 (The Pile)

Max Activating Token Index: 619