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

Dataset: The Pile

Neuron 1958 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8454. Min Range: -3.8454

Max Act: 3.6160. Min Act: -0.0000

Data Index: 1256993 (The Pile)

Max Activating Token Index: 421

Text #1

Max Range: 3.8454. Min Range: -3.8454

Max Act: 3.7130. Min Act: -0.0000

Data Index: 1709955 (The Pile)

Max Activating Token Index: 718

Text #2

Max Range: 3.8454. Min Range: -3.8454

Max Act: 3.7442. Min Act: -0.0000

Data Index: 480797 (The Pile)

Max Activating Token Index: 541

Text #3

Max Range: 3.8454. Min Range: -3.8454

Max Act: 3.7305. Min Act: -0.0000

Data Index: 1400133 (The Pile)

Max Activating Token Index: 515

Text #4

Max Range: 3.8454. Min Range: -3.8454

Max Act: 3.8454. Min Act: -0.0000

Data Index: 1493841 (The Pile)

Max Activating Token Index: 374

Text #5

Max Range: 3.8454. Min Range: -3.8454

Max Act: 3.5900. Min Act: -0.0000

Data Index: 680457 (The Pile)

Max Activating Token Index: 331

Text #6

Max Range: 3.8454. Min Range: -3.8454

Max Act: 3.4057. Min Act: -0.0000

Data Index: 581292 (The Pile)

Max Activating Token Index: 540

Text #7

Max Range: 3.8454. Min Range: -3.8454

Max Act: 3.3025. Min Act: -0.0000

Data Index: 1284246 (The Pile)

Max Activating Token Index: 827

Text #8

Max Range: 3.8454. Min Range: -3.8454

Max Act: 3.5138. Min Act: -0.0000

Data Index: 1682434 (The Pile)

Max Activating Token Index: 611

Text #9

Max Range: 3.8454. Min Range: -3.8454

Max Act: 3.2628. Min Act: -0.0000

Data Index: 1518597 (The Pile)

Max Activating Token Index: 46

Text #10

Max Range: 3.8454. Min Range: -3.8454

Max Act: 3.3509. Min Act: -0.0000

Data Index: 220770 (The Pile)

Max Activating Token Index: 610

Text #11

Max Range: 3.8454. Min Range: -3.8454

Max Act: 3.1661. Min Act: -0.0000

Data Index: 1794146 (The Pile)

Max Activating Token Index: 483

Text #12

Max Range: 3.8454. Min Range: -3.8454

Max Act: 3.0047. Min Act: -0.0000

Data Index: 803530 (The Pile)

Max Activating Token Index: 483

Text #13

Max Range: 3.8454. Min Range: -3.8454

Max Act: 3.1917. Min Act: -0.0000

Data Index: 967013 (The Pile)

Max Activating Token Index: 583

Text #14

Max Range: 3.8454. Min Range: -3.8454

Max Act: 3.0418. Min Act: -0.0000

Data Index: 600681 (The Pile)

Max Activating Token Index: 462

Text #15

Max Range: 3.8454. Min Range: -3.8454

Max Act: 3.1705. Min Act: -0.0000

Data Index: 980855 (The Pile)

Max Activating Token Index: 419

Text #16

Max Range: 3.8454. Min Range: -3.8454

Max Act: 3.1539. Min Act: -0.0000

Data Index: 1977454 (The Pile)

Max Activating Token Index: 355

Text #17

Max Range: 3.8454. Min Range: -3.8454

Max Act: 3.1044. Min Act: -0.0000

Data Index: 71706 (The Pile)

Max Activating Token Index: 180

Text #18

Max Range: 3.8454. Min Range: -3.8454

Max Act: 2.9570. Min Act: -0.0000

Data Index: 1603405 (The Pile)

Max Activating Token Index: 301

Text #19

Max Range: 3.8454. Min Range: -3.8454

Max Act: 3.2224. Min Act: -0.0000

Data Index: 1019827 (The Pile)

Max Activating Token Index: 535