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

Dataset: The Pile

Neuron 722 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: 0.1810. Min Range: -0.1810

Max Act: 0.1810. Min Act: -0.0000

Data Index: 1641923 (The Pile)

Max Activating Token Index: 770

Text #1

Max Range: 0.1810. Min Range: -0.1810

Max Act: 0.1591. Min Act: -0.0000

Data Index: 724053 (The Pile)

Max Activating Token Index: 119

Text #2

Max Range: 0.1810. Min Range: -0.1810

Max Act: 0.1482. Min Act: -0.0000

Data Index: 1191633 (The Pile)

Max Activating Token Index: 877

Text #3

Max Range: 0.1810. Min Range: -0.1810

Max Act: 0.1339. Min Act: -0.0000

Data Index: 1473534 (The Pile)

Max Activating Token Index: 801

Text #4

Max Range: 0.1810. Min Range: -0.1810

Max Act: 0.1382. Min Act: -0.0000

Data Index: 1650064 (The Pile)

Max Activating Token Index: 555

Text #5

Max Range: 0.1810. Min Range: -0.1810

Max Act: 0.1320. Min Act: -0.0000

Data Index: 1175555 (The Pile)

Max Activating Token Index: 99

Text #6

Max Range: 0.1810. Min Range: -0.1810

Max Act: 0.1219. Min Act: -0.0000

Data Index: 378186 (The Pile)

Max Activating Token Index: 486

Text #7

Max Range: 0.1810. Min Range: -0.1810

Max Act: 0.1357. Min Act: -0.0000

Data Index: 1666067 (The Pile)

Max Activating Token Index: 628

Text #8

Max Range: 0.1810. Min Range: -0.1810

Max Act: 0.1215. Min Act: -0.0000

Data Index: 746324 (The Pile)

Max Activating Token Index: 493

Text #9

Max Range: 0.1810. Min Range: -0.1810

Max Act: 0.1187. Min Act: -0.0000

Data Index: 1189561 (The Pile)

Max Activating Token Index: 812

Text #10

Max Range: 0.1810. Min Range: -0.1810

Max Act: 0.1042. Min Act: -0.0000

Data Index: 592862 (The Pile)

Max Activating Token Index: 775

Text #11

Max Range: 0.1810. Min Range: -0.1810

Max Act: 0.1214. Min Act: -0.0000

Data Index: 1387400 (The Pile)

Max Activating Token Index: 786

Text #12

Max Range: 0.1810. Min Range: -0.1810

Max Act: 0.1123. Min Act: -0.0000

Data Index: 1926681 (The Pile)

Max Activating Token Index: 883

Text #13

Max Range: 0.1810. Min Range: -0.1810

Max Act: 0.0997. Min Act: -0.0000

Data Index: 797366 (The Pile)

Max Activating Token Index: 755

Text #14

Max Range: 0.1810. Min Range: -0.1810

Max Act: 0.1262. Min Act: -0.0000

Data Index: 161974 (The Pile)

Max Activating Token Index: 368

Text #15

Max Range: 0.1810. Min Range: -0.1810

Max Act: 0.1141. Min Act: -0.0000

Data Index: 489872 (The Pile)

Max Activating Token Index: 146

Text #16

Max Range: 0.1810. Min Range: -0.1810

Max Act: 0.1127. Min Act: -0.0000

Data Index: 1044132 (The Pile)

Max Activating Token Index: 556

Text #17

Max Range: 0.1810. Min Range: -0.1810

Max Act: 0.1123. Min Act: -0.0000

Data Index: 346704 (The Pile)

Max Activating Token Index: 906

Text #18

Max Range: 0.1810. Min Range: -0.1810

Max Act: 0.1108. Min Act: -0.0000

Data Index: 640822 (The Pile)

Max Activating Token Index: 553

Text #19

Max Range: 0.1810. Min Range: -0.1810

Max Act: 0.1136. Min Act: -0.0000

Data Index: 1121312 (The Pile)

Max Activating Token Index: 772