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

Dataset: The Pile

Neuron 3972 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: 3.9397. Min Range: -3.9397

Max Act: 3.9397. Min Act: -0.0000

Data Index: 900053 (The Pile)

Max Activating Token Index: 908

Text #1

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.7011. Min Act: -0.0000

Data Index: 884351 (The Pile)

Max Activating Token Index: 197

Text #2

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.8295. Min Act: -0.0000

Data Index: 585109 (The Pile)

Max Activating Token Index: 125

Text #3

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.2510. Min Act: -0.0000

Data Index: 377916 (The Pile)

Max Activating Token Index: 551

Text #4

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.3803. Min Act: -0.0000

Data Index: 1892856 (The Pile)

Max Activating Token Index: 825

Text #5

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.1694. Min Act: -0.0000

Data Index: 1299613 (The Pile)

Max Activating Token Index: 775

Text #6

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.4170. Min Act: -0.0000

Data Index: 1912930 (The Pile)

Max Activating Token Index: 736

Text #7

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.1058. Min Act: -0.0000

Data Index: 1080506 (The Pile)

Max Activating Token Index: 54

Text #8

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.3098. Min Act: -0.0000

Data Index: 1337926 (The Pile)

Max Activating Token Index: 582

Text #9

Max Range: 3.9397. Min Range: -3.9397

Max Act: 2.9736. Min Act: -0.0000

Data Index: 1238887 (The Pile)

Max Activating Token Index: 773

Text #10

Max Range: 3.9397. Min Range: -3.9397

Max Act: 2.8088. Min Act: -0.0000

Data Index: 594053 (The Pile)

Max Activating Token Index: 400

Text #11

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.0513. Min Act: -0.0000

Data Index: 783298 (The Pile)

Max Activating Token Index: 396

Text #12

Max Range: 3.9397. Min Range: -3.9397

Max Act: 2.9119. Min Act: -0.0000

Data Index: 188425 (The Pile)

Max Activating Token Index: 288

Text #13

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.1603. Min Act: -0.0000

Data Index: 703460 (The Pile)

Max Activating Token Index: 126

Text #14

Max Range: 3.9397. Min Range: -3.9397

Max Act: 2.9998. Min Act: -0.0000

Data Index: 1409888 (The Pile)

Max Activating Token Index: 421

Text #15

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.2503. Min Act: -0.0000

Data Index: 1562831 (The Pile)

Max Activating Token Index: 736

Text #16

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.0898. Min Act: -0.0000

Data Index: 955515 (The Pile)

Max Activating Token Index: 209

Text #17

Max Range: 3.9397. Min Range: -3.9397

Max Act: 2.8060. Min Act: -0.0000

Data Index: 315354 (The Pile)

Max Activating Token Index: 433

Text #18

Max Range: 3.9397. Min Range: -3.9397

Max Act: 2.6371. Min Act: -0.0000

Data Index: 1195457 (The Pile)

Max Activating Token Index: 645

Text #19

Max Range: 3.9397. Min Range: -3.9397

Max Act: 3.0338. Min Act: -0.0000

Data Index: 903661 (The Pile)

Max Activating Token Index: 336