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

Dataset: The Pile

Neuron 138 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1712. Min Range: -1.1712

Max Act: 1.1712. Min Act: -0.0000

Data Index: 566196 (The Pile)

Max Activating Token Index: 208

Text #1

Max Range: 1.1712. Min Range: -1.1712

Max Act: 1.0696. Min Act: -0.0000

Data Index: 1205083 (The Pile)

Max Activating Token Index: 832

Text #2

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.7831. Min Act: -0.0000

Data Index: 545335 (The Pile)

Max Activating Token Index: 517

Text #3

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.9283. Min Act: -0.0000

Data Index: 1349649 (The Pile)

Max Activating Token Index: 744

Text #4

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.8066. Min Act: -0.0000

Data Index: 1808557 (The Pile)

Max Activating Token Index: 442

Text #5

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.8074. Min Act: -0.0000

Data Index: 441010 (The Pile)

Max Activating Token Index: 714

Text #6

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.7911. Min Act: -0.0000

Data Index: 724923 (The Pile)

Max Activating Token Index: 651

Text #7

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.7942. Min Act: -0.0000

Data Index: 899755 (The Pile)

Max Activating Token Index: 648

Text #8

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.8967. Min Act: -0.0000

Data Index: 1252281 (The Pile)

Max Activating Token Index: 310

Text #9

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.7763. Min Act: -0.0000

Data Index: 216714 (The Pile)

Max Activating Token Index: 21

Text #10

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.8805. Min Act: -0.0000

Data Index: 1944283 (The Pile)

Max Activating Token Index: 795

Text #11

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.8398. Min Act: -0.0000

Data Index: 690294 (The Pile)

Max Activating Token Index: 584

Text #12

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.9576. Min Act: -0.0000

Data Index: 475159 (The Pile)

Max Activating Token Index: 650

Text #13

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.8257. Min Act: -0.0000

Data Index: 373299 (The Pile)

Max Activating Token Index: 452

Text #14

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.7844. Min Act: -0.0000

Data Index: 1903543 (The Pile)

Max Activating Token Index: 735

Text #15

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.7518. Min Act: -0.0000

Data Index: 1667633 (The Pile)

Max Activating Token Index: 156

Text #16

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.7837. Min Act: -0.0000

Data Index: 1881207 (The Pile)

Max Activating Token Index: 358

Text #17

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.7397. Min Act: -0.0000

Data Index: 1592682 (The Pile)

Max Activating Token Index: 430

Text #18

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.7710. Min Act: -0.0000

Data Index: 1867375 (The Pile)

Max Activating Token Index: 183

Text #19

Max Range: 1.1712. Min Range: -1.1712

Max Act: 0.7647. Min Act: -0.0000

Data Index: 1778081 (The Pile)

Max Activating Token Index: 398