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

Dataset: The Pile

Neuron 1062 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1513. Min Range: -1.1513

Max Act: 1.1513. Min Act: -0.0000

Data Index: 707417 (The Pile)

Max Activating Token Index: 359

Text #1

Max Range: 1.1513. Min Range: -1.1513

Max Act: 1.1128. Min Act: -0.0000

Data Index: 842791 (The Pile)

Max Activating Token Index: 423

Text #2

Max Range: 1.1513. Min Range: -1.1513

Max Act: 1.1062. Min Act: -0.0000

Data Index: 992312 (The Pile)

Max Activating Token Index: 610

Text #3

Max Range: 1.1513. Min Range: -1.1513

Max Act: 1.0146. Min Act: -0.0000

Data Index: 1412225 (The Pile)

Max Activating Token Index: 487

Text #4

Max Range: 1.1513. Min Range: -1.1513

Max Act: 1.0430. Min Act: -0.0000

Data Index: 87786 (The Pile)

Max Activating Token Index: 358

Text #5

Max Range: 1.1513. Min Range: -1.1513

Max Act: 1.1067. Min Act: -0.0000

Data Index: 405983 (The Pile)

Max Activating Token Index: 423

Text #6

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.9604. Min Act: -0.0000

Data Index: 1475627 (The Pile)

Max Activating Token Index: 379

Text #7

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.9617. Min Act: -0.0000

Data Index: 1637077 (The Pile)

Max Activating Token Index: 577

Text #8

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.9041. Min Act: -0.0000

Data Index: 83414 (The Pile)

Max Activating Token Index: 696

Text #9

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.9673. Min Act: -0.0000

Data Index: 110929 (The Pile)

Max Activating Token Index: 598

Text #10

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.8642. Min Act: -0.0000

Data Index: 1130345 (The Pile)

Max Activating Token Index: 555

Text #11

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.7792. Min Act: -0.0000

Data Index: 806009 (The Pile)

Max Activating Token Index: 705

Text #12

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.9270. Min Act: -0.0000

Data Index: 30302 (The Pile)

Max Activating Token Index: 524

Text #13

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.9935. Min Act: -0.0000

Data Index: 350201 (The Pile)

Max Activating Token Index: 296

Text #14

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.8995. Min Act: -0.0000

Data Index: 121729 (The Pile)

Max Activating Token Index: 492

Text #15

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.8975. Min Act: -0.0000

Data Index: 1777110 (The Pile)

Max Activating Token Index: 399

Text #16

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.8535. Min Act: -0.0000

Data Index: 360840 (The Pile)

Max Activating Token Index: 377

Text #17

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.7895. Min Act: -0.0000

Data Index: 1129021 (The Pile)

Max Activating Token Index: 623

Text #18

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.8186. Min Act: -0.0000

Data Index: 854390 (The Pile)

Max Activating Token Index: 831

Text #19

Max Range: 1.1513. Min Range: -1.1513

Max Act: 0.7755. Min Act: -0.0000

Data Index: 1824848 (The Pile)

Max Activating Token Index: 494