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

Dataset: The Pile

Neuron 147 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: 3.1914. Min Range: -3.1914

Max Act: 3.1914. Min Act: -0.0000

Data Index: 1033892 (The Pile)

Max Activating Token Index: 860

Text #1

Max Range: 3.1914. Min Range: -3.1914

Max Act: 3.0396. Min Act: -0.0000

Data Index: 1356233 (The Pile)

Max Activating Token Index: 393

Text #2

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.6902. Min Act: -0.0000

Data Index: 377999 (The Pile)

Max Activating Token Index: 23

Text #3

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.6876. Min Act: -0.0000

Data Index: 166876 (The Pile)

Max Activating Token Index: 751

Text #4

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.5426. Min Act: -0.0000

Data Index: 222674 (The Pile)

Max Activating Token Index: 968

Text #5

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.6728. Min Act: -0.0000

Data Index: 314194 (The Pile)

Max Activating Token Index: 313

Text #6

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.5136. Min Act: -0.0000

Data Index: 1396248 (The Pile)

Max Activating Token Index: 230

Text #7

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.5727. Min Act: -0.0000

Data Index: 1041197 (The Pile)

Max Activating Token Index: 32

Text #8

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.5508. Min Act: -0.0000

Data Index: 907687 (The Pile)

Max Activating Token Index: 783

Text #9

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.5470. Min Act: -0.0000

Data Index: 1474309 (The Pile)

Max Activating Token Index: 930

Text #10

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.5952. Min Act: -0.0000

Data Index: 1757171 (The Pile)

Max Activating Token Index: 447

Text #11

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.4686. Min Act: -0.0000

Data Index: 1531004 (The Pile)

Max Activating Token Index: 254

Text #12

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.4566. Min Act: -0.0000

Data Index: 1532538 (The Pile)

Max Activating Token Index: 315

Text #13

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.4350. Min Act: -0.0000

Data Index: 1616917 (The Pile)

Max Activating Token Index: 814

Text #14

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.4987. Min Act: -0.0000

Data Index: 360960 (The Pile)

Max Activating Token Index: 857

Text #15

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.5498. Min Act: -0.0000

Data Index: 1224513 (The Pile)

Max Activating Token Index: 299

Text #16

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.5019. Min Act: -0.0000

Data Index: 12502 (The Pile)

Max Activating Token Index: 218

Text #17

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.3944. Min Act: -0.0000

Data Index: 213849 (The Pile)

Max Activating Token Index: 18

Text #18

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.5151. Min Act: -0.0000

Data Index: 1548560 (The Pile)

Max Activating Token Index: 389

Text #19

Max Range: 3.1914. Min Range: -3.1914

Max Act: 2.2815. Min Act: -0.0000

Data Index: 510221 (The Pile)

Max Activating Token Index: 446