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

Dataset: The Pile

Neuron 3772 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: 1.4773. Min Range: -1.4773

Max Act: 1.4773. Min Act: -0.0000

Data Index: 893461 (The Pile)

Max Activating Token Index: 391

Text #1

Max Range: 1.4773. Min Range: -1.4773

Max Act: 1.3030. Min Act: -0.0000

Data Index: 588444 (The Pile)

Max Activating Token Index: 229

Text #2

Max Range: 1.4773. Min Range: -1.4773

Max Act: 1.2365. Min Act: -0.0000

Data Index: 1649996 (The Pile)

Max Activating Token Index: 305

Text #3

Max Range: 1.4773. Min Range: -1.4773

Max Act: 1.3483. Min Act: -0.0000

Data Index: 1495081 (The Pile)

Max Activating Token Index: 493

Text #4

Max Range: 1.4773. Min Range: -1.4773

Max Act: 1.3284. Min Act: -0.0000

Data Index: 974488 (The Pile)

Max Activating Token Index: 37

Text #5

Max Range: 1.4773. Min Range: -1.4773

Max Act: 1.3137. Min Act: -0.0000

Data Index: 1477182 (The Pile)

Max Activating Token Index: 145

Text #6

Max Range: 1.4773. Min Range: -1.4773

Max Act: 1.3251. Min Act: -0.0000

Data Index: 351345 (The Pile)

Max Activating Token Index: 285

Text #7

Max Range: 1.4773. Min Range: -1.4773

Max Act: 1.2941. Min Act: -0.0000

Data Index: 1706881 (The Pile)

Max Activating Token Index: 226

Text #8

Max Range: 1.4773. Min Range: -1.4773

Max Act: 1.2687. Min Act: -0.0000

Data Index: 1939043 (The Pile)

Max Activating Token Index: 603

Text #9

Max Range: 1.4773. Min Range: -1.4773

Max Act: 1.0764. Min Act: -0.0000

Data Index: 1028424 (The Pile)

Max Activating Token Index: 661

Text #10

Max Range: 1.4773. Min Range: -1.4773

Max Act: 1.1132. Min Act: -0.0000

Data Index: 1672352 (The Pile)

Max Activating Token Index: 519

Text #11

Max Range: 1.4773. Min Range: -1.4773

Max Act: 1.1028. Min Act: -0.0000

Data Index: 1639157 (The Pile)

Max Activating Token Index: 883

Text #12

Max Range: 1.4773. Min Range: -1.4773

Max Act: 1.0626. Min Act: -0.0000

Data Index: 1622468 (The Pile)

Max Activating Token Index: 444

Text #13

Max Range: 1.4773. Min Range: -1.4773

Max Act: 1.1085. Min Act: -0.0000

Data Index: 1751694 (The Pile)

Max Activating Token Index: 393

Text #14

Max Range: 1.4773. Min Range: -1.4773

Max Act: 1.2105. Min Act: -0.0000

Data Index: 879535 (The Pile)

Max Activating Token Index: 350

Text #15

Max Range: 1.4773. Min Range: -1.4773

Max Act: 1.0200. Min Act: -0.0000

Data Index: 743495 (The Pile)

Max Activating Token Index: 907

Text #16

Max Range: 1.4773. Min Range: -1.4773

Max Act: 1.0467. Min Act: -0.0000

Data Index: 951276 (The Pile)

Max Activating Token Index: 147

Text #17

Max Range: 1.4773. Min Range: -1.4773

Max Act: 1.0245. Min Act: -0.0000

Data Index: 415460 (The Pile)

Max Activating Token Index: 734

Text #18

Max Range: 1.4773. Min Range: -1.4773

Max Act: 1.2511. Min Act: -0.0001

Data Index: 961720 (The Pile)

Max Activating Token Index: 43

Text #19

Max Range: 1.4773. Min Range: -1.4773

Max Act: 0.9690. Min Act: -0.0000

Data Index: 215960 (The Pile)

Max Activating Token Index: 621