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

Dataset: The Pile

Neuron 1220 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1773. Min Act: -0.0000

Data Index: 384320 (The Pile)

Max Activating Token Index: 392

Text #1

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1761. Min Act: -0.0000

Data Index: 1994645 (The Pile)

Max Activating Token Index: 327

Text #2

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1730. Min Act: -0.0000

Data Index: 247226 (The Pile)

Max Activating Token Index: 411

Text #3

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1726. Min Act: -0.0000

Data Index: 1491183 (The Pile)

Max Activating Token Index: 369

Text #4

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1713. Min Act: -0.0000

Data Index: 1258415 (The Pile)

Max Activating Token Index: 450

Text #5

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1717. Min Act: -0.0000

Data Index: 975469 (The Pile)

Max Activating Token Index: 386

Text #6

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1715. Min Act: -0.0000

Data Index: 389929 (The Pile)

Max Activating Token Index: 386

Text #7

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1705. Min Act: -0.0000

Data Index: 77808 (The Pile)

Max Activating Token Index: 550

Text #8

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1760. Min Act: -0.0000

Data Index: 1511135 (The Pile)

Max Activating Token Index: 292

Text #9

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1685. Min Act: -0.0000

Data Index: 253803 (The Pile)

Max Activating Token Index: 1009

Text #10

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1680. Min Act: -0.0000

Data Index: 1606114 (The Pile)

Max Activating Token Index: 385

Text #11

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1681. Min Act: -0.0000

Data Index: 1033774 (The Pile)

Max Activating Token Index: 276

Text #12

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1679. Min Act: -0.0000

Data Index: 140469 (The Pile)

Max Activating Token Index: 470

Text #13

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1670. Min Act: -0.0000

Data Index: 326860 (The Pile)

Max Activating Token Index: 243

Text #14

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1617. Min Act: -0.0000

Data Index: 1790450 (The Pile)

Max Activating Token Index: 316

Text #15

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1667. Min Act: -0.0000

Data Index: 790428 (The Pile)

Max Activating Token Index: 351

Text #16

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1616. Min Act: -0.0000

Data Index: 239528 (The Pile)

Max Activating Token Index: 432

Text #17

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1667. Min Act: -0.0000

Data Index: 1548693 (The Pile)

Max Activating Token Index: 437

Text #18

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1669. Min Act: -0.0000

Data Index: 1114121 (The Pile)

Max Activating Token Index: 146

Text #19

Max Range: 0.1773. Min Range: -0.1773

Max Act: 0.1670. Min Act: -0.0000

Data Index: 1942072 (The Pile)

Max Activating Token Index: 124