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

Dataset: The Pile

Neuron 919 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: 0.6864. Min Range: -0.6864

Max Act: 0.6864. Min Act: -0.0000

Data Index: 1099607 (The Pile)

Max Activating Token Index: 677

Text #1

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.6166. Min Act: -0.0000

Data Index: 1291473 (The Pile)

Max Activating Token Index: 779

Text #2

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.6060. Min Act: -0.0000

Data Index: 1173575 (The Pile)

Max Activating Token Index: 219

Text #3

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.6032. Min Act: -0.0000

Data Index: 180739 (The Pile)

Max Activating Token Index: 302

Text #4

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.5412. Min Act: -0.0000

Data Index: 290264 (The Pile)

Max Activating Token Index: 987

Text #5

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.5580. Min Act: -0.0000

Data Index: 1140003 (The Pile)

Max Activating Token Index: 65

Text #6

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.5372. Min Act: -0.0000

Data Index: 284688 (The Pile)

Max Activating Token Index: 920

Text #7

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.5447. Min Act: -0.0000

Data Index: 1873976 (The Pile)

Max Activating Token Index: 980

Text #8

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.5061. Min Act: -0.0000

Data Index: 589532 (The Pile)

Max Activating Token Index: 680

Text #9

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.5822. Min Act: -0.0000

Data Index: 1651137 (The Pile)

Max Activating Token Index: 800

Text #10

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.5468. Min Act: -0.0000

Data Index: 1466017 (The Pile)

Max Activating Token Index: 325

Text #11

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.5095. Min Act: -0.0000

Data Index: 1497577 (The Pile)

Max Activating Token Index: 997

Text #12

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.5087. Min Act: -0.0000

Data Index: 431481 (The Pile)

Max Activating Token Index: 334

Text #13

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.5360. Min Act: -0.0000

Data Index: 1792402 (The Pile)

Max Activating Token Index: 676

Text #14

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.5222. Min Act: -0.0000

Data Index: 1589390 (The Pile)

Max Activating Token Index: 311

Text #15

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.5242. Min Act: -0.0000

Data Index: 207462 (The Pile)

Max Activating Token Index: 581

Text #16

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.4834. Min Act: -0.0000

Data Index: 624015 (The Pile)

Max Activating Token Index: 936

Text #17

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.5106. Min Act: -0.0000

Data Index: 594592 (The Pile)

Max Activating Token Index: 365

Text #18

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.4627. Min Act: -0.0000

Data Index: 988193 (The Pile)

Max Activating Token Index: 217

Text #19

Max Range: 0.6864. Min Range: -0.6864

Max Act: 0.4553. Min Act: -0.0000

Data Index: 1872564 (The Pile)

Max Activating Token Index: 329