Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 1835 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2926. Min Act: -0.0000

Data Index: 568088 (The Pile)

Max Activating Token Index: 822

Text #1

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2644. Min Act: -0.0000

Data Index: 1388306 (The Pile)

Max Activating Token Index: 820

Text #2

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2833. Min Act: -0.0000

Data Index: 400621 (The Pile)

Max Activating Token Index: 980

Text #3

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.2251. Min Act: -0.0000

Data Index: 85678 (The Pile)

Max Activating Token Index: 898

Text #4

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1946. Min Act: -0.0000

Data Index: 1734646 (The Pile)

Max Activating Token Index: 261

Text #5

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1941. Min Act: -0.0000

Data Index: 720587 (The Pile)

Max Activating Token Index: 885

Text #6

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1818. Min Act: -0.0000

Data Index: 1852794 (The Pile)

Max Activating Token Index: 493

Text #7

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1751. Min Act: -0.0001

Data Index: 1879717 (The Pile)

Max Activating Token Index: 948

Text #8

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1740. Min Act: -0.0000

Data Index: 1485234 (The Pile)

Max Activating Token Index: 609

Text #9

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1721. Min Act: -0.0000

Data Index: 370459 (The Pile)

Max Activating Token Index: 877

Text #10

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1738. Min Act: -0.0000

Data Index: 1612303 (The Pile)

Max Activating Token Index: 823

Text #11

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1673. Min Act: -0.0001

Data Index: 221710 (The Pile)

Max Activating Token Index: 861

Text #12

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1658. Min Act: -0.0000

Data Index: 585206 (The Pile)

Max Activating Token Index: 741

Text #13

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1647. Min Act: -0.0000

Data Index: 1532140 (The Pile)

Max Activating Token Index: 762

Text #14

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1642. Min Act: -0.0000

Data Index: 1211039 (The Pile)

Max Activating Token Index: 255

Text #15

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1494. Min Act: -0.0000

Data Index: 424982 (The Pile)

Max Activating Token Index: 957

Text #16

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1578. Min Act: -0.0000

Data Index: 798161 (The Pile)

Max Activating Token Index: 113

Text #17

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1565. Min Act: -0.0000

Data Index: 710707 (The Pile)

Max Activating Token Index: 423

Text #18

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1640. Min Act: -0.0000

Data Index: 57545 (The Pile)

Max Activating Token Index: 242

Text #19

Max Range: 0.2926. Min Range: -0.2926

Max Act: 0.1552. Min Act: -0.0000

Data Index: 418207 (The Pile)

Max Activating Token Index: 492