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

Dataset: The Pile

Neuron 664 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: 0.3656. Min Range: -0.3656

Max Act: 0.3656. Min Act: -0.0000

Data Index: 582284 (The Pile)

Max Activating Token Index: 832

Text #1

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.3227. Min Act: -0.0000

Data Index: 265318 (The Pile)

Max Activating Token Index: 685

Text #2

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.2821. Min Act: -0.0000

Data Index: 1849570 (The Pile)

Max Activating Token Index: 339

Text #3

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.2417. Min Act: -0.0000

Data Index: 1968640 (The Pile)

Max Activating Token Index: 902

Text #4

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.2105. Min Act: -0.0000

Data Index: 19578 (The Pile)

Max Activating Token Index: 438

Text #5

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.2115. Min Act: -0.0000

Data Index: 1800945 (The Pile)

Max Activating Token Index: 343

Text #6

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.1951. Min Act: -0.0000

Data Index: 1136529 (The Pile)

Max Activating Token Index: 396

Text #7

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.1935. Min Act: -0.0000

Data Index: 489689 (The Pile)

Max Activating Token Index: 130

Text #8

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.1979. Min Act: -0.0000

Data Index: 317091 (The Pile)

Max Activating Token Index: 498

Text #9

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.1651. Min Act: -0.0000

Data Index: 1547806 (The Pile)

Max Activating Token Index: 549

Text #10

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.1842. Min Act: -0.0000

Data Index: 134004 (The Pile)

Max Activating Token Index: 306

Text #11

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.1670. Min Act: -0.0000

Data Index: 95671 (The Pile)

Max Activating Token Index: 559

Text #12

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.1637. Min Act: -0.0000

Data Index: 204882 (The Pile)

Max Activating Token Index: 784

Text #13

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.1737. Min Act: 0.0000

Data Index: 778297 (The Pile)

Max Activating Token Index: 558

Text #14

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.1806. Min Act: -0.0000

Data Index: 187680 (The Pile)

Max Activating Token Index: 736

Text #15

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.1803. Min Act: -0.0000

Data Index: 1969237 (The Pile)

Max Activating Token Index: 771

Text #16

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.1729. Min Act: -0.0000

Data Index: 1894257 (The Pile)

Max Activating Token Index: 574

Text #17

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.1691. Min Act: -0.0000

Data Index: 1851118 (The Pile)

Max Activating Token Index: 444

Text #18

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.1689. Min Act: -0.0000

Data Index: 896272 (The Pile)

Max Activating Token Index: 752

Text #19

Max Range: 0.3656. Min Range: -0.3656

Max Act: 0.1623. Min Act: -0.0000

Data Index: 1908868 (The Pile)

Max Activating Token Index: 428