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

Dataset: The Pile

Neuron 5040 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.5234. Min Act: -0.0000

Data Index: 767691 (The Pile)

Max Activating Token Index: 81

Text #1

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.5110. Min Act: -0.0000

Data Index: 1036554 (The Pile)

Max Activating Token Index: 978

Text #2

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.4543. Min Act: -0.0000

Data Index: 1746011 (The Pile)

Max Activating Token Index: 126

Text #3

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.4593. Min Act: -0.0000

Data Index: 532195 (The Pile)

Max Activating Token Index: 372

Text #4

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.4518. Min Act: -0.0000

Data Index: 1683567 (The Pile)

Max Activating Token Index: 242

Text #5

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.4501. Min Act: -0.0000

Data Index: 403785 (The Pile)

Max Activating Token Index: 55

Text #6

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.4159. Min Act: -0.0000

Data Index: 178232 (The Pile)

Max Activating Token Index: 692

Text #7

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.4077. Min Act: -0.0000

Data Index: 59324 (The Pile)

Max Activating Token Index: 360

Text #8

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.4115. Min Act: -0.0000

Data Index: 1616591 (The Pile)

Max Activating Token Index: 195

Text #9

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.4147. Min Act: -0.0000

Data Index: 591252 (The Pile)

Max Activating Token Index: 205

Text #10

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.4009. Min Act: -0.0000

Data Index: 1541017 (The Pile)

Max Activating Token Index: 112

Text #11

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.4100. Min Act: -0.0000

Data Index: 1879164 (The Pile)

Max Activating Token Index: 584

Text #12

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3832. Min Act: -0.0000

Data Index: 1972793 (The Pile)

Max Activating Token Index: 466

Text #13

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3815. Min Act: -0.0000

Data Index: 233610 (The Pile)

Max Activating Token Index: 952

Text #14

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3918. Min Act: -0.0000

Data Index: 354191 (The Pile)

Max Activating Token Index: 263

Text #15

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3766. Min Act: -0.0000

Data Index: 596636 (The Pile)

Max Activating Token Index: 31

Text #16

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3681. Min Act: -0.0000

Data Index: 161897 (The Pile)

Max Activating Token Index: 533

Text #17

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3383. Min Act: -0.0000

Data Index: 452825 (The Pile)

Max Activating Token Index: 437

Text #18

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3785. Min Act: -0.0000

Data Index: 480874 (The Pile)

Max Activating Token Index: 753

Text #19

Max Range: 0.5234. Min Range: -0.5234

Max Act: 0.3530. Min Act: -0.0000

Data Index: 1690816 (The Pile)

Max Activating Token Index: 832