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

Dataset: The Pile

Neuron 1602 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: 0.3067. Min Range: -0.3067

Max Act: 0.3058. Min Act: -0.0000

Data Index: 1289672 (The Pile)

Max Activating Token Index: 852

Text #1

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.3067. Min Act: -0.0000

Data Index: 993252 (The Pile)

Max Activating Token Index: 339

Text #2

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2412. Min Act: -0.0000

Data Index: 298612 (The Pile)

Max Activating Token Index: 219

Text #3

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.2099. Min Act: -0.0000

Data Index: 200260 (The Pile)

Max Activating Token Index: 680

Text #4

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1977. Min Act: -0.0000

Data Index: 912485 (The Pile)

Max Activating Token Index: 317

Text #5

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1841. Min Act: -0.0000

Data Index: 1745069 (The Pile)

Max Activating Token Index: 561

Text #6

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1941. Min Act: -0.0000

Data Index: 1619094 (The Pile)

Max Activating Token Index: 321

Text #7

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1642. Min Act: -0.0000

Data Index: 1828660 (The Pile)

Max Activating Token Index: 503

Text #8

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1722. Min Act: -0.0000

Data Index: 631934 (The Pile)

Max Activating Token Index: 219

Text #9

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1715. Min Act: -0.0000

Data Index: 1092533 (The Pile)

Max Activating Token Index: 580

Text #10

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1702. Min Act: -0.0000

Data Index: 1437698 (The Pile)

Max Activating Token Index: 1003

Text #11

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1504. Min Act: -0.0000

Data Index: 258907 (The Pile)

Max Activating Token Index: 736

Text #12

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1687. Min Act: -0.0000

Data Index: 1263236 (The Pile)

Max Activating Token Index: 231

Text #13

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1669. Min Act: -0.0000

Data Index: 1419716 (The Pile)

Max Activating Token Index: 981

Text #14

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1493. Min Act: -0.0000

Data Index: 362091 (The Pile)

Max Activating Token Index: 715

Text #15

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1666. Min Act: -0.0000

Data Index: 33941 (The Pile)

Max Activating Token Index: 544

Text #16

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1665. Min Act: -0.0000

Data Index: 1689495 (The Pile)

Max Activating Token Index: 344

Text #17

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1595. Min Act: -0.0000

Data Index: 152749 (The Pile)

Max Activating Token Index: 754

Text #18

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1537. Min Act: -0.0000

Data Index: 1193479 (The Pile)

Max Activating Token Index: 793

Text #19

Max Range: 0.3067. Min Range: -0.3067

Max Act: 0.1549. Min Act: -0.0000

Data Index: 806310 (The Pile)

Max Activating Token Index: 663