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

Dataset: The Pile

Neuron 5070 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1600. Min Act: -0.0000

Data Index: 1321614 (The Pile)

Max Activating Token Index: 832

Text #1

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1486. Min Act: -0.0000

Data Index: 1412592 (The Pile)

Max Activating Token Index: 56

Text #2

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1407. Min Act: -0.0000

Data Index: 1708188 (The Pile)

Max Activating Token Index: 232

Text #3

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1469. Min Act: -0.0000

Data Index: 709165 (The Pile)

Max Activating Token Index: 608

Text #4

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1510. Min Act: -0.0000

Data Index: 307482 (The Pile)

Max Activating Token Index: 836

Text #5

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1453. Min Act: -0.0000

Data Index: 1028318 (The Pile)

Max Activating Token Index: 293

Text #6

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1290. Min Act: -0.0000

Data Index: 15313 (The Pile)

Max Activating Token Index: 799

Text #7

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1328. Min Act: -0.0000

Data Index: 361768 (The Pile)

Max Activating Token Index: 130

Text #8

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1139. Min Act: -0.0000

Data Index: 378090 (The Pile)

Max Activating Token Index: 517

Text #9

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1262. Min Act: -0.0000

Data Index: 38620 (The Pile)

Max Activating Token Index: 486

Text #10

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1252. Min Act: -0.0000

Data Index: 405204 (The Pile)

Max Activating Token Index: 823

Text #11

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1289. Min Act: -0.0000

Data Index: 1837307 (The Pile)

Max Activating Token Index: 386

Text #12

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1242. Min Act: -0.0000

Data Index: 251178 (The Pile)

Max Activating Token Index: 487

Text #13

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1151. Min Act: -0.0000

Data Index: 1034879 (The Pile)

Max Activating Token Index: 561

Text #14

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1147. Min Act: -0.0000

Data Index: 286546 (The Pile)

Max Activating Token Index: 567

Text #15

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1101. Min Act: -0.0000

Data Index: 655616 (The Pile)

Max Activating Token Index: 440

Text #16

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1135. Min Act: -0.0000

Data Index: 58861 (The Pile)

Max Activating Token Index: 801

Text #17

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1014. Min Act: -0.0000

Data Index: 1040350 (The Pile)

Max Activating Token Index: 759

Text #18

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1133. Min Act: -0.0000

Data Index: 1014069 (The Pile)

Max Activating Token Index: 571

Text #19

Max Range: 0.1600. Min Range: -0.1600

Max Act: 0.1110. Min Act: -0.0000

Data Index: 1827505 (The Pile)

Max Activating Token Index: 716