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

Dataset: The Pile

Neuron 4110 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: 0.3012. Min Range: -0.3012

Max Act: 0.3012. Min Act: -0.0000

Data Index: 1390928 (The Pile)

Max Activating Token Index: 438

Text #1

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2295. Min Act: -0.0000

Data Index: 1582871 (The Pile)

Max Activating Token Index: 320

Text #2

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2002. Min Act: -0.0000

Data Index: 1787650 (The Pile)

Max Activating Token Index: 30

Text #3

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2350. Min Act: -0.0000

Data Index: 1936593 (The Pile)

Max Activating Token Index: 293

Text #4

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2049. Min Act: -0.0000

Data Index: 648430 (The Pile)

Max Activating Token Index: 288

Text #5

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2157. Min Act: -0.0000

Data Index: 1497102 (The Pile)

Max Activating Token Index: 295

Text #6

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2155. Min Act: -0.0000

Data Index: 1493652 (The Pile)

Max Activating Token Index: 139

Text #7

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2114. Min Act: -0.0000

Data Index: 1791806 (The Pile)

Max Activating Token Index: 775

Text #8

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.1968. Min Act: -0.0000

Data Index: 1944829 (The Pile)

Max Activating Token Index: 930

Text #9

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2177. Min Act: -0.0000

Data Index: 492882 (The Pile)

Max Activating Token Index: 334

Text #10

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2015. Min Act: -0.0000

Data Index: 1678994 (The Pile)

Max Activating Token Index: 305

Text #11

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.1986. Min Act: -0.0000

Data Index: 618475 (The Pile)

Max Activating Token Index: 559

Text #12

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.1982. Min Act: -0.0000

Data Index: 1201147 (The Pile)

Max Activating Token Index: 437

Text #13

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2108. Min Act: -0.0000

Data Index: 360520 (The Pile)

Max Activating Token Index: 969

Text #14

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.1761. Min Act: -0.0000

Data Index: 332864 (The Pile)

Max Activating Token Index: 371

Text #15

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.1948. Min Act: -0.0000

Data Index: 1934668 (The Pile)

Max Activating Token Index: 22

Text #16

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.1962. Min Act: -0.0000

Data Index: 1476291 (The Pile)

Max Activating Token Index: 193

Text #17

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.2010. Min Act: -0.0000

Data Index: 1106759 (The Pile)

Max Activating Token Index: 278

Text #18

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.1919. Min Act: -0.0000

Data Index: 698436 (The Pile)

Max Activating Token Index: 412

Text #19

Max Range: 0.3012. Min Range: -0.3012

Max Act: 0.1909. Min Act: -0.0000

Data Index: 1689798 (The Pile)

Max Activating Token Index: 384