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

Dataset: The Pile

Neuron 77 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.2616. Min Act: -0.0000

Data Index: 382004 (The Pile)

Max Activating Token Index: 197

Text #1

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1976. Min Act: -0.0000

Data Index: 1701291 (The Pile)

Max Activating Token Index: 376

Text #2

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.2034. Min Act: -0.0000

Data Index: 1111314 (The Pile)

Max Activating Token Index: 538

Text #3

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1849. Min Act: -0.0000

Data Index: 651000 (The Pile)

Max Activating Token Index: 758

Text #4

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.2059. Min Act: -0.0000

Data Index: 158664 (The Pile)

Max Activating Token Index: 491

Text #5

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1593. Min Act: -0.0000

Data Index: 622950 (The Pile)

Max Activating Token Index: 307

Text #6

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1788. Min Act: -0.0000

Data Index: 874980 (The Pile)

Max Activating Token Index: 178

Text #7

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1841. Min Act: -0.0000

Data Index: 1554401 (The Pile)

Max Activating Token Index: 376

Text #8

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1689. Min Act: -0.0000

Data Index: 402807 (The Pile)

Max Activating Token Index: 444

Text #9

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1523. Min Act: -0.0000

Data Index: 1693582 (The Pile)

Max Activating Token Index: 118

Text #10

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1735. Min Act: -0.0000

Data Index: 1921763 (The Pile)

Max Activating Token Index: 948

Text #11

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1642. Min Act: -0.0000

Data Index: 1561470 (The Pile)

Max Activating Token Index: 149

Text #12

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1542. Min Act: -0.0000

Data Index: 1682695 (The Pile)

Max Activating Token Index: 374

Text #13

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1428. Min Act: -0.0000

Data Index: 292302 (The Pile)

Max Activating Token Index: 789

Text #14

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1408. Min Act: -0.0000

Data Index: 24744 (The Pile)

Max Activating Token Index: 847

Text #15

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1514. Min Act: -0.0000

Data Index: 923580 (The Pile)

Max Activating Token Index: 58

Text #16

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1411. Min Act: -0.0000

Data Index: 191374 (The Pile)

Max Activating Token Index: 925

Text #17

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1473. Min Act: -0.0000

Data Index: 1487022 (The Pile)

Max Activating Token Index: 864

Text #18

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1737. Min Act: -0.0000

Data Index: 1870832 (The Pile)

Max Activating Token Index: 307

Text #19

Max Range: 0.2616. Min Range: -0.2616

Max Act: 0.1564. Min Act: -0.0000

Data Index: 1050716 (The Pile)

Max Activating Token Index: 73