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

Dataset: The Pile

Neuron 3682 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4752. Min Range: -1.4752

Max Act: 1.4752. Min Act: -0.0000

Data Index: 1529174 (The Pile)

Max Activating Token Index: 202

Text #1

Max Range: 1.4752. Min Range: -1.4752

Max Act: 0.8645. Min Act: 0.0000

Data Index: 1556162 (The Pile)

Max Activating Token Index: 543

Text #2

Max Range: 1.4752. Min Range: -1.4752

Max Act: 0.7474. Min Act: -0.0000

Data Index: 475894 (The Pile)

Max Activating Token Index: 164

Text #3

Max Range: 1.4752. Min Range: -1.4752

Max Act: 0.7014. Min Act: -0.0000

Data Index: 401805 (The Pile)

Max Activating Token Index: 492

Text #4

Max Range: 1.4752. Min Range: -1.4752

Max Act: 0.6530. Min Act: -0.0000

Data Index: 1983485 (The Pile)

Max Activating Token Index: 916

Text #5

Max Range: 1.4752. Min Range: -1.4752

Max Act: 0.6755. Min Act: -0.0000

Data Index: 1903790 (The Pile)

Max Activating Token Index: 195

Text #6

Max Range: 1.4752. Min Range: -1.4752

Max Act: 0.7696. Min Act: -0.0000

Data Index: 1657351 (The Pile)

Max Activating Token Index: 612

Text #7

Max Range: 1.4752. Min Range: -1.4752

Max Act: 0.7621. Min Act: -0.0000

Data Index: 465704 (The Pile)

Max Activating Token Index: 775

Text #8

Max Range: 1.4752. Min Range: -1.4752

Max Act: 0.6769. Min Act: -0.0000

Data Index: 712624 (The Pile)

Max Activating Token Index: 957

Text #9

Max Range: 1.4752. Min Range: -1.4752

Max Act: 0.6523. Min Act: -0.0000

Data Index: 1757948 (The Pile)

Max Activating Token Index: 1004

Text #10

Max Range: 1.4752. Min Range: -1.4752

Max Act: 0.6625. Min Act: -0.0000

Data Index: 1726021 (The Pile)

Max Activating Token Index: 483

Text #11

Max Range: 1.4752. Min Range: -1.4752

Max Act: 0.6544. Min Act: -0.0000

Data Index: 904590 (The Pile)

Max Activating Token Index: 890

Text #12

Max Range: 1.4752. Min Range: -1.4752

Max Act: 0.6503. Min Act: 0.0000

Data Index: 252814 (The Pile)

Max Activating Token Index: 936

Text #13

Max Range: 1.4752. Min Range: -1.4752

Max Act: 0.6673. Min Act: -0.0000

Data Index: 1361218 (The Pile)

Max Activating Token Index: 777

Text #14

Max Range: 1.4752. Min Range: -1.4752

Max Act: 0.6030. Min Act: -0.0000

Data Index: 1530843 (The Pile)

Max Activating Token Index: 936

Text #15

Max Range: 1.4752. Min Range: -1.4752

Max Act: 0.5736. Min Act: -0.0000

Data Index: 1506594 (The Pile)

Max Activating Token Index: 401

Text #16

Max Range: 1.4752. Min Range: -1.4752

Max Act: 0.5508. Min Act: -0.0000

Data Index: 924686 (The Pile)

Max Activating Token Index: 760

Text #17

Max Range: 1.4752. Min Range: -1.4752

Max Act: 0.6227. Min Act: -0.0000

Data Index: 1626605 (The Pile)

Max Activating Token Index: 211

Text #18

Max Range: 1.4752. Min Range: -1.4752

Max Act: 0.6151. Min Act: -0.0000

Data Index: 1790181 (The Pile)

Max Activating Token Index: 534

Text #19

Max Range: 1.4752. Min Range: -1.4752

Max Act: 0.6000. Min Act: -0.0000

Data Index: 1738298 (The Pile)

Max Activating Token Index: 846