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

Dataset: The Pile

Neuron 2112 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.8075. Min Act: -0.0000

Data Index: 1587744 (The Pile)

Max Activating Token Index: 170

Text #1

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.8067. Min Act: -0.0000

Data Index: 907375 (The Pile)

Max Activating Token Index: 679

Text #2

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6839. Min Act: -0.0000

Data Index: 130664 (The Pile)

Max Activating Token Index: 133

Text #3

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.7943. Min Act: -0.0000

Data Index: 1639522 (The Pile)

Max Activating Token Index: 510

Text #4

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6817. Min Act: -0.0001

Data Index: 500275 (The Pile)

Max Activating Token Index: 535

Text #5

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6669. Min Act: -0.0000

Data Index: 186555 (The Pile)

Max Activating Token Index: 592

Text #6

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.7943. Min Act: -0.0001

Data Index: 581084 (The Pile)

Max Activating Token Index: 602

Text #7

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.7203. Min Act: -0.0000

Data Index: 395545 (The Pile)

Max Activating Token Index: 580

Text #8

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.7235. Min Act: -0.0000

Data Index: 1705924 (The Pile)

Max Activating Token Index: 34

Text #9

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6441. Min Act: -0.0001

Data Index: 1144662 (The Pile)

Max Activating Token Index: 251

Text #10

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6290. Min Act: -0.0000

Data Index: 451932 (The Pile)

Max Activating Token Index: 287

Text #11

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6204. Min Act: -0.0000

Data Index: 170263 (The Pile)

Max Activating Token Index: 276

Text #12

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6041. Min Act: -0.0000

Data Index: 1095726 (The Pile)

Max Activating Token Index: 800

Text #13

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5991. Min Act: -0.0000

Data Index: 1500408 (The Pile)

Max Activating Token Index: 21

Text #14

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5773. Min Act: -0.0000

Data Index: 512482 (The Pile)

Max Activating Token Index: 177

Text #15

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6494. Min Act: -0.0000

Data Index: 1816453 (The Pile)

Max Activating Token Index: 935

Text #16

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6252. Min Act: -0.0001

Data Index: 1424496 (The Pile)

Max Activating Token Index: 377

Text #17

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6265. Min Act: -0.0000

Data Index: 305929 (The Pile)

Max Activating Token Index: 363

Text #18

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.6099. Min Act: -0.0000

Data Index: 82646 (The Pile)

Max Activating Token Index: 800

Text #19

Max Range: 0.8075. Min Range: -0.8075

Max Act: 0.5498. Min Act: -0.0000

Data Index: 1276495 (The Pile)

Max Activating Token Index: 658