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

Dataset: The Pile

Neuron 4555 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: 0.4752. Min Range: -0.4752

Max Act: 0.4752. Min Act: -0.0000

Data Index: 1546418 (The Pile)

Max Activating Token Index: 414

Text #1

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.4484. Min Act: -0.0000

Data Index: 340652 (The Pile)

Max Activating Token Index: 257

Text #2

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.4549. Min Act: -0.0000

Data Index: 672514 (The Pile)

Max Activating Token Index: 993

Text #3

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.4238. Min Act: -0.0000

Data Index: 1680735 (The Pile)

Max Activating Token Index: 239

Text #4

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.4251. Min Act: -0.0000

Data Index: 221171 (The Pile)

Max Activating Token Index: 18

Text #5

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.4629. Min Act: -0.0000

Data Index: 1504658 (The Pile)

Max Activating Token Index: 91

Text #6

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.4602. Min Act: -0.0000

Data Index: 970885 (The Pile)

Max Activating Token Index: 587

Text #7

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.4310. Min Act: -0.0000

Data Index: 535021 (The Pile)

Max Activating Token Index: 455

Text #8

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.3902. Min Act: -0.0000

Data Index: 1878232 (The Pile)

Max Activating Token Index: 817

Text #9

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.4350. Min Act: -0.0000

Data Index: 414185 (The Pile)

Max Activating Token Index: 34

Text #10

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.4043. Min Act: -0.0000

Data Index: 1131557 (The Pile)

Max Activating Token Index: 218

Text #11

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.3895. Min Act: -0.0000

Data Index: 1847456 (The Pile)

Max Activating Token Index: 1013

Text #12

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.3980. Min Act: -0.0000

Data Index: 573816 (The Pile)

Max Activating Token Index: 383

Text #13

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.3955. Min Act: -0.0000

Data Index: 1040971 (The Pile)

Max Activating Token Index: 161

Text #14

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.4072. Min Act: -0.0000

Data Index: 693089 (The Pile)

Max Activating Token Index: 203

Text #15

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.3992. Min Act: -0.0000

Data Index: 1969983 (The Pile)

Max Activating Token Index: 993

Text #16

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.4126. Min Act: -0.0000

Data Index: 1752167 (The Pile)

Max Activating Token Index: 859

Text #17

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.3531. Min Act: -0.0000

Data Index: 1341209 (The Pile)

Max Activating Token Index: 730

Text #18

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.4053. Min Act: -0.0000

Data Index: 1683157 (The Pile)

Max Activating Token Index: 264

Text #19

Max Range: 0.4752. Min Range: -0.4752

Max Act: 0.3944. Min Act: -0.0000

Data Index: 751118 (The Pile)

Max Activating Token Index: 200