Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2291 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.7773. Min Act: -0.0000

Data Index: 55606 (The Pile)

Max Activating Token Index: 795

Text #1

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.7934. Min Act: -0.0000

Data Index: 1464687 (The Pile)

Max Activating Token Index: 428

Text #2

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.7186. Min Act: -0.0000

Data Index: 1085588 (The Pile)

Max Activating Token Index: 654

Text #3

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.6449. Min Act: -0.0000

Data Index: 1353138 (The Pile)

Max Activating Token Index: 706

Text #4

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.6649. Min Act: -0.0000

Data Index: 619144 (The Pile)

Max Activating Token Index: 889

Text #5

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.6263. Min Act: -0.0000

Data Index: 1719604 (The Pile)

Max Activating Token Index: 666

Text #6

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.5677. Min Act: -0.0000

Data Index: 352063 (The Pile)

Max Activating Token Index: 401

Text #7

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.6611. Min Act: -0.0000

Data Index: 1292990 (The Pile)

Max Activating Token Index: 400

Text #8

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.5889. Min Act: -0.0000

Data Index: 1659985 (The Pile)

Max Activating Token Index: 887

Text #9

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.6108. Min Act: -0.0000

Data Index: 1577473 (The Pile)

Max Activating Token Index: 47

Text #10

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.5617. Min Act: -0.0000

Data Index: 1986610 (The Pile)

Max Activating Token Index: 116

Text #11

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.5379. Min Act: -0.0000

Data Index: 1687307 (The Pile)

Max Activating Token Index: 858

Text #12

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.5698. Min Act: -0.0000

Data Index: 1401990 (The Pile)

Max Activating Token Index: 624

Text #13

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.5167. Min Act: -0.0000

Data Index: 1481080 (The Pile)

Max Activating Token Index: 177

Text #14

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.5991. Min Act: -0.0000

Data Index: 594709 (The Pile)

Max Activating Token Index: 480

Text #15

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.5116. Min Act: -0.0000

Data Index: 1984292 (The Pile)

Max Activating Token Index: 966

Text #16

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.5321. Min Act: -0.0000

Data Index: 714618 (The Pile)

Max Activating Token Index: 365

Text #17

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.4143. Min Act: -0.0000

Data Index: 480580 (The Pile)

Max Activating Token Index: 33

Text #18

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.5160. Min Act: -0.0000

Data Index: 344659 (The Pile)

Max Activating Token Index: 487

Text #19

Max Range: 0.7934. Min Range: -0.7934

Max Act: 0.5129. Min Act: -0.0000

Data Index: 351649 (The Pile)

Max Activating Token Index: 287