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

Dataset: The Pile

Neuron 4 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: 1.1707. Min Range: -1.1707

Max Act: 1.1707. Min Act: -0.0000

Data Index: 962796 (The Pile)

Max Activating Token Index: 307

Text #1

Max Range: 1.1707. Min Range: -1.1707

Max Act: 0.8875. Min Act: -0.0000

Data Index: 1982786 (The Pile)

Max Activating Token Index: 559

Text #2

Max Range: 1.1707. Min Range: -1.1707

Max Act: 1.0828. Min Act: -0.0000

Data Index: 856313 (The Pile)

Max Activating Token Index: 220

Text #3

Max Range: 1.1707. Min Range: -1.1707

Max Act: 0.9561. Min Act: -0.0000

Data Index: 965443 (The Pile)

Max Activating Token Index: 1012

Text #4

Max Range: 1.1707. Min Range: -1.1707

Max Act: 1.0736. Min Act: -0.0000

Data Index: 1082488 (The Pile)

Max Activating Token Index: 199

Text #5

Max Range: 1.1707. Min Range: -1.1707

Max Act: 0.8736. Min Act: -0.0000

Data Index: 1916602 (The Pile)

Max Activating Token Index: 65

Text #6

Max Range: 1.1707. Min Range: -1.1707

Max Act: 0.9235. Min Act: -0.0000

Data Index: 1346329 (The Pile)

Max Activating Token Index: 770

Text #7

Max Range: 1.1707. Min Range: -1.1707

Max Act: 1.0239. Min Act: -0.0000

Data Index: 1991083 (The Pile)

Max Activating Token Index: 246

Text #8

Max Range: 1.1707. Min Range: -1.1707

Max Act: 0.8744. Min Act: -0.0000

Data Index: 1274100 (The Pile)

Max Activating Token Index: 526

Text #9

Max Range: 1.1707. Min Range: -1.1707

Max Act: 0.9478. Min Act: -0.0000

Data Index: 1788342 (The Pile)

Max Activating Token Index: 486

Text #10

Max Range: 1.1707. Min Range: -1.1707

Max Act: 0.8902. Min Act: -0.0000

Data Index: 269839 (The Pile)

Max Activating Token Index: 990

Text #11

Max Range: 1.1707. Min Range: -1.1707

Max Act: 0.9266. Min Act: -0.0000

Data Index: 1157031 (The Pile)

Max Activating Token Index: 669

Text #12

Max Range: 1.1707. Min Range: -1.1707

Max Act: 0.9453. Min Act: -0.0000

Data Index: 1908098 (The Pile)

Max Activating Token Index: 646

Text #13

Max Range: 1.1707. Min Range: -1.1707

Max Act: 0.9581. Min Act: -0.0000

Data Index: 895045 (The Pile)

Max Activating Token Index: 766

Text #14

Max Range: 1.1707. Min Range: -1.1707

Max Act: 0.9252. Min Act: -0.0000

Data Index: 567513 (The Pile)

Max Activating Token Index: 409

Text #15

Max Range: 1.1707. Min Range: -1.1707

Max Act: 0.7838. Min Act: -0.0000

Data Index: 824353 (The Pile)

Max Activating Token Index: 234

Text #16

Max Range: 1.1707. Min Range: -1.1707

Max Act: 0.8322. Min Act: -0.0000

Data Index: 1302213 (The Pile)

Max Activating Token Index: 882

Text #17

Max Range: 1.1707. Min Range: -1.1707

Max Act: 0.8424. Min Act: -0.0000

Data Index: 60909 (The Pile)

Max Activating Token Index: 683

Text #18

Max Range: 1.1707. Min Range: -1.1707

Max Act: 0.8553. Min Act: -0.0000

Data Index: 812537 (The Pile)

Max Activating Token Index: 672

Text #19

Max Range: 1.1707. Min Range: -1.1707

Max Act: 0.8313. Min Act: -0.0000

Data Index: 1042544 (The Pile)

Max Activating Token Index: 235