Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 126 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.9795. Min Act: -0.0000

Data Index: 1169236 (The Pile)

Max Activating Token Index: 547

Text #1

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.8510. Min Act: -0.0000

Data Index: 1002156 (The Pile)

Max Activating Token Index: 488

Text #2

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.9393. Min Act: -0.0000

Data Index: 990860 (The Pile)

Max Activating Token Index: 805

Text #3

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.8119. Min Act: -0.0000

Data Index: 1031778 (The Pile)

Max Activating Token Index: 623

Text #4

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.9337. Min Act: -0.0000

Data Index: 648020 (The Pile)

Max Activating Token Index: 603

Text #5

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.9245. Min Act: -0.0000

Data Index: 1801345 (The Pile)

Max Activating Token Index: 547

Text #6

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.9474. Min Act: -0.0000

Data Index: 405431 (The Pile)

Max Activating Token Index: 468

Text #7

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.8331. Min Act: -0.0000

Data Index: 132923 (The Pile)

Max Activating Token Index: 393

Text #8

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.8607. Min Act: -0.0000

Data Index: 961356 (The Pile)

Max Activating Token Index: 653

Text #9

Max Range: 1.0005. Min Range: -1.0005

Max Act: 1.0005. Min Act: -0.0000

Data Index: 592015 (The Pile)

Max Activating Token Index: 507

Text #10

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.8909. Min Act: -0.0000

Data Index: 71102 (The Pile)

Max Activating Token Index: 503

Text #11

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.9326. Min Act: -0.0000

Data Index: 1192924 (The Pile)

Max Activating Token Index: 519

Text #12

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.9320. Min Act: -0.0000

Data Index: 117290 (The Pile)

Max Activating Token Index: 152

Text #13

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.8981. Min Act: -0.0000

Data Index: 1666251 (The Pile)

Max Activating Token Index: 962

Text #14

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.8926. Min Act: -0.0000

Data Index: 756728 (The Pile)

Max Activating Token Index: 832

Text #15

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.8330. Min Act: -0.0000

Data Index: 563406 (The Pile)

Max Activating Token Index: 468

Text #16

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.8616. Min Act: -0.0000

Data Index: 1915935 (The Pile)

Max Activating Token Index: 522

Text #17

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.8258. Min Act: -0.0000

Data Index: 446539 (The Pile)

Max Activating Token Index: 676

Text #18

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.9420. Min Act: -0.0000

Data Index: 1678531 (The Pile)

Max Activating Token Index: 350

Text #19

Max Range: 1.0005. Min Range: -1.0005

Max Act: 0.8281. Min Act: -0.0000

Data Index: 1101892 (The Pile)

Max Activating Token Index: 693