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

Dataset: The Pile

Neuron 710 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: 0.1467. Min Range: -0.1467

Max Act: 0.1467. Min Act: -0.0000

Data Index: 1836240 (The Pile)

Max Activating Token Index: 246

Text #1

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.0815. Min Act: -0.0000

Data Index: 1761647 (The Pile)

Max Activating Token Index: 716

Text #2

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.0839. Min Act: -0.0000

Data Index: 194996 (The Pile)

Max Activating Token Index: 972

Text #3

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.0800. Min Act: -0.0000

Data Index: 1332608 (The Pile)

Max Activating Token Index: 162

Text #4

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.0797. Min Act: -0.0000

Data Index: 1935946 (The Pile)

Max Activating Token Index: 886

Text #5

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.0709. Min Act: -0.0000

Data Index: 1410140 (The Pile)

Max Activating Token Index: 793

Text #6

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.0744. Min Act: -0.0000

Data Index: 43889 (The Pile)

Max Activating Token Index: 803

Text #7

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.0730. Min Act: -0.0000

Data Index: 454110 (The Pile)

Max Activating Token Index: 867

Text #8

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.0731. Min Act: -0.0000

Data Index: 55937 (The Pile)

Max Activating Token Index: 180

Text #9

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.0714. Min Act: -0.0000

Data Index: 1274298 (The Pile)

Max Activating Token Index: 41

Text #10

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.0616. Min Act: -0.0000

Data Index: 384336 (The Pile)

Max Activating Token Index: 95

Text #11

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.0690. Min Act: -0.0000

Data Index: 162040 (The Pile)

Max Activating Token Index: 340

Text #12

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.0558. Min Act: -0.0000

Data Index: 377078 (The Pile)

Max Activating Token Index: 966

Text #13

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.0653. Min Act: -0.0000

Data Index: 559963 (The Pile)

Max Activating Token Index: 791

Text #14

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.0700. Min Act: -0.0000

Data Index: 1521291 (The Pile)

Max Activating Token Index: 973

Text #15

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.0622. Min Act: -0.0000

Data Index: 904676 (The Pile)

Max Activating Token Index: 365

Text #16

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.0630. Min Act: -0.0000

Data Index: 484413 (The Pile)

Max Activating Token Index: 139

Text #17

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.0607. Min Act: -0.0000

Data Index: 58475 (The Pile)

Max Activating Token Index: 481

Text #18

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.0629. Min Act: -0.0000

Data Index: 1928942 (The Pile)

Max Activating Token Index: 431

Text #19

Max Range: 0.1467. Min Range: -0.1467

Max Act: 0.0632. Min Act: -0.0000

Data Index: 585122 (The Pile)

Max Activating Token Index: 238