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

Dataset: The Pile

Neuron 212 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: 0.5388. Min Range: -0.5388

Max Act: 0.5388. Min Act: -0.0000

Data Index: 1574226 (The Pile)

Max Activating Token Index: 270

Text #1

Max Range: 0.5388. Min Range: -0.5388

Max Act: 0.4815. Min Act: -0.0000

Data Index: 1114880 (The Pile)

Max Activating Token Index: 195

Text #2

Max Range: 0.5388. Min Range: -0.5388

Max Act: 0.4458. Min Act: -0.0000

Data Index: 1734949 (The Pile)

Max Activating Token Index: 294

Text #3

Max Range: 0.5388. Min Range: -0.5388

Max Act: 0.4522. Min Act: -0.0000

Data Index: 281460 (The Pile)

Max Activating Token Index: 62

Text #4

Max Range: 0.5388. Min Range: -0.5388

Max Act: 0.4056. Min Act: -0.0000

Data Index: 403714 (The Pile)

Max Activating Token Index: 310

Text #5

Max Range: 0.5388. Min Range: -0.5388

Max Act: 0.4118. Min Act: -0.0000

Data Index: 1281381 (The Pile)

Max Activating Token Index: 99

Text #6

Max Range: 0.5388. Min Range: -0.5388

Max Act: 0.4214. Min Act: -0.0000

Data Index: 113242 (The Pile)

Max Activating Token Index: 470

Text #7

Max Range: 0.5388. Min Range: -0.5388

Max Act: 0.4275. Min Act: -0.0000

Data Index: 393211 (The Pile)

Max Activating Token Index: 344

Text #8

Max Range: 0.5388. Min Range: -0.5388

Max Act: 0.4135. Min Act: -0.0000

Data Index: 1745775 (The Pile)

Max Activating Token Index: 141

Text #9

Max Range: 0.5388. Min Range: -0.5388

Max Act: 0.3959. Min Act: -0.0000

Data Index: 1671780 (The Pile)

Max Activating Token Index: 230

Text #10

Max Range: 0.5388. Min Range: -0.5388

Max Act: 0.4082. Min Act: -0.0000

Data Index: 970693 (The Pile)

Max Activating Token Index: 320

Text #11

Max Range: 0.5388. Min Range: -0.5388

Max Act: 0.3977. Min Act: -0.0000

Data Index: 626665 (The Pile)

Max Activating Token Index: 547

Text #12

Max Range: 0.5388. Min Range: -0.5388

Max Act: 0.3845. Min Act: -0.0000

Data Index: 1833166 (The Pile)

Max Activating Token Index: 34

Text #13

Max Range: 0.5388. Min Range: -0.5388

Max Act: 0.3984. Min Act: -0.0000

Data Index: 978851 (The Pile)

Max Activating Token Index: 324

Text #14

Max Range: 0.5388. Min Range: -0.5388

Max Act: 0.3845. Min Act: -0.0000

Data Index: 916504 (The Pile)

Max Activating Token Index: 381

Text #15

Max Range: 0.5388. Min Range: -0.5388

Max Act: 0.3868. Min Act: -0.0000

Data Index: 942936 (The Pile)

Max Activating Token Index: 568

Text #16

Max Range: 0.5388. Min Range: -0.5388

Max Act: 0.3800. Min Act: -0.0000

Data Index: 1748806 (The Pile)

Max Activating Token Index: 127

Text #17

Max Range: 0.5388. Min Range: -0.5388

Max Act: 0.3773. Min Act: -0.0000

Data Index: 1212850 (The Pile)

Max Activating Token Index: 330

Text #18

Max Range: 0.5388. Min Range: -0.5388

Max Act: 0.3851. Min Act: -0.0000

Data Index: 770824 (The Pile)

Max Activating Token Index: 455

Text #19

Max Range: 0.5388. Min Range: -0.5388

Max Act: 0.3600. Min Act: -0.0000

Data Index: 1483801 (The Pile)

Max Activating Token Index: 406