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

Dataset: The Pile

Neuron 3391 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: 0.1524. Min Range: -0.1524

Max Act: 0.1524. Min Act: -0.0000

Data Index: 737306 (The Pile)

Max Activating Token Index: 867

Text #1

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1471. Min Act: -0.0000

Data Index: 916233 (The Pile)

Max Activating Token Index: 618

Text #2

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1318. Min Act: -0.0000

Data Index: 1637406 (The Pile)

Max Activating Token Index: 194

Text #3

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1329. Min Act: -0.0000

Data Index: 790117 (The Pile)

Max Activating Token Index: 480

Text #4

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1149. Min Act: -0.0000

Data Index: 1030624 (The Pile)

Max Activating Token Index: 597

Text #5

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1177. Min Act: -0.0000

Data Index: 1947959 (The Pile)

Max Activating Token Index: 112

Text #6

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1108. Min Act: -0.0000

Data Index: 227208 (The Pile)

Max Activating Token Index: 356

Text #7

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1184. Min Act: -0.0000

Data Index: 657741 (The Pile)

Max Activating Token Index: 573

Text #8

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1046. Min Act: -0.0000

Data Index: 1862714 (The Pile)

Max Activating Token Index: 273

Text #9

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1112. Min Act: -0.0000

Data Index: 1890141 (The Pile)

Max Activating Token Index: 844

Text #10

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1068. Min Act: -0.0000

Data Index: 980029 (The Pile)

Max Activating Token Index: 297

Text #11

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1029. Min Act: -0.0000

Data Index: 1933800 (The Pile)

Max Activating Token Index: 755

Text #12

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1017. Min Act: -0.0000

Data Index: 391761 (The Pile)

Max Activating Token Index: 436

Text #13

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1026. Min Act: -0.0000

Data Index: 1142216 (The Pile)

Max Activating Token Index: 820

Text #14

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1009. Min Act: -0.0000

Data Index: 1380344 (The Pile)

Max Activating Token Index: 195

Text #15

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0964. Min Act: -0.0000

Data Index: 640727 (The Pile)

Max Activating Token Index: 115

Text #16

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0994. Min Act: -0.0000

Data Index: 668450 (The Pile)

Max Activating Token Index: 11

Text #17

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.1072. Min Act: -0.0000

Data Index: 727815 (The Pile)

Max Activating Token Index: 16

Text #18

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0995. Min Act: -0.0000

Data Index: 1382228 (The Pile)

Max Activating Token Index: 298

Text #19

Max Range: 0.1524. Min Range: -0.1524

Max Act: 0.0953. Min Act: -0.0000

Data Index: 1660321 (The Pile)

Max Activating Token Index: 57