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

Dataset: The Pile

Neuron 443 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1830. Min Act: -0.0000

Data Index: 145217 (The Pile)

Max Activating Token Index: 808

Text #1

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1891. Min Act: -0.0000

Data Index: 372249 (The Pile)

Max Activating Token Index: 254

Text #2

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1667. Min Act: -0.0000

Data Index: 473889 (The Pile)

Max Activating Token Index: 44

Text #3

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1716. Min Act: -0.0000

Data Index: 637306 (The Pile)

Max Activating Token Index: 553

Text #4

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1475. Min Act: -0.0000

Data Index: 692344 (The Pile)

Max Activating Token Index: 580

Text #5

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1561. Min Act: -0.0000

Data Index: 1697907 (The Pile)

Max Activating Token Index: 366

Text #6

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1470. Min Act: -0.0000

Data Index: 1425483 (The Pile)

Max Activating Token Index: 448

Text #7

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1343. Min Act: -0.0000

Data Index: 1956787 (The Pile)

Max Activating Token Index: 83

Text #8

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1288. Min Act: -0.0000

Data Index: 1091426 (The Pile)

Max Activating Token Index: 677

Text #9

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1399. Min Act: -0.0000

Data Index: 1053625 (The Pile)

Max Activating Token Index: 202

Text #10

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1290. Min Act: -0.0000

Data Index: 101981 (The Pile)

Max Activating Token Index: 976

Text #11

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1377. Min Act: -0.0000

Data Index: 806459 (The Pile)

Max Activating Token Index: 817

Text #12

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1362. Min Act: -0.0000

Data Index: 1059711 (The Pile)

Max Activating Token Index: 688

Text #13

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1316. Min Act: -0.0000

Data Index: 55819 (The Pile)

Max Activating Token Index: 479

Text #14

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1246. Min Act: -0.0000

Data Index: 531701 (The Pile)

Max Activating Token Index: 393

Text #15

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1235. Min Act: -0.0000

Data Index: 1339934 (The Pile)

Max Activating Token Index: 144

Text #16

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1185. Min Act: -0.0000

Data Index: 740211 (The Pile)

Max Activating Token Index: 766

Text #17

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1143. Min Act: -0.0000

Data Index: 257105 (The Pile)

Max Activating Token Index: 1005

Text #18

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1378. Min Act: -0.0000

Data Index: 1640027 (The Pile)

Max Activating Token Index: 446

Text #19

Max Range: 0.1891. Min Range: -0.1891

Max Act: 0.1237. Min Act: -0.0000

Data Index: 767912 (The Pile)

Max Activating Token Index: 270