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

Dataset: The Pile

Neuron 979 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: 3.6653. Min Range: -3.6653

Max Act: 3.6653. Min Act: -0.0000

Data Index: 555185 (The Pile)

Max Activating Token Index: 902

Text #1

Max Range: 3.6653. Min Range: -3.6653

Max Act: 3.3340. Min Act: -0.0000

Data Index: 774249 (The Pile)

Max Activating Token Index: 23

Text #2

Max Range: 3.6653. Min Range: -3.6653

Max Act: 2.5744. Min Act: -0.0000

Data Index: 878489 (The Pile)

Max Activating Token Index: 82

Text #3

Max Range: 3.6653. Min Range: -3.6653

Max Act: 2.3918. Min Act: -0.0000

Data Index: 245009 (The Pile)

Max Activating Token Index: 759

Text #4

Max Range: 3.6653. Min Range: -3.6653

Max Act: 2.3758. Min Act: -0.0000

Data Index: 1511041 (The Pile)

Max Activating Token Index: 873

Text #5

Max Range: 3.6653. Min Range: -3.6653

Max Act: 2.3575. Min Act: -0.0000

Data Index: 374527 (The Pile)

Max Activating Token Index: 150

Text #6

Max Range: 3.6653. Min Range: -3.6653

Max Act: 2.2028. Min Act: -0.0000

Data Index: 1052529 (The Pile)

Max Activating Token Index: 300

Text #7

Max Range: 3.6653. Min Range: -3.6653

Max Act: 2.3167. Min Act: -0.0000

Data Index: 1782805 (The Pile)

Max Activating Token Index: 175

Text #8

Max Range: 3.6653. Min Range: -3.6653

Max Act: 2.3176. Min Act: -0.0000

Data Index: 34001 (The Pile)

Max Activating Token Index: 184

Text #9

Max Range: 3.6653. Min Range: -3.6653

Max Act: 2.1628. Min Act: -0.0000

Data Index: 1719899 (The Pile)

Max Activating Token Index: 475

Text #10

Max Range: 3.6653. Min Range: -3.6653

Max Act: 2.2568. Min Act: -0.0000

Data Index: 34244 (The Pile)

Max Activating Token Index: 514

Text #11

Max Range: 3.6653. Min Range: -3.6653

Max Act: 2.1078. Min Act: -0.0000

Data Index: 1667634 (The Pile)

Max Activating Token Index: 237

Text #12

Max Range: 3.6653. Min Range: -3.6653

Max Act: 2.2171. Min Act: -0.0000

Data Index: 696363 (The Pile)

Max Activating Token Index: 958

Text #13

Max Range: 3.6653. Min Range: -3.6653

Max Act: 2.0592. Min Act: -0.0000

Data Index: 1513261 (The Pile)

Max Activating Token Index: 582

Text #14

Max Range: 3.6653. Min Range: -3.6653

Max Act: 2.1141. Min Act: -0.0000

Data Index: 878564 (The Pile)

Max Activating Token Index: 372

Text #15

Max Range: 3.6653. Min Range: -3.6653

Max Act: 2.0840. Min Act: -0.0000

Data Index: 1441975 (The Pile)

Max Activating Token Index: 232

Text #16

Max Range: 3.6653. Min Range: -3.6653

Max Act: 2.0927. Min Act: -0.0000

Data Index: 786901 (The Pile)

Max Activating Token Index: 329

Text #17

Max Range: 3.6653. Min Range: -3.6653

Max Act: 1.9937. Min Act: -0.0000

Data Index: 398508 (The Pile)

Max Activating Token Index: 23

Text #18

Max Range: 3.6653. Min Range: -3.6653

Max Act: 1.8848. Min Act: -0.0000

Data Index: 1528814 (The Pile)

Max Activating Token Index: 727

Text #19

Max Range: 3.6653. Min Range: -3.6653

Max Act: 1.9713. Min Act: -0.0000

Data Index: 1613601 (The Pile)

Max Activating Token Index: 813