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

Dataset: The Pile

Neuron 5112 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: 0.4668. Min Range: -0.4668

Max Act: 0.4668. Min Act: -0.0000

Data Index: 25320 (The Pile)

Max Activating Token Index: 752

Text #1

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.4043. Min Act: -0.0000

Data Index: 1751409 (The Pile)

Max Activating Token Index: 294

Text #2

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3768. Min Act: -0.0000

Data Index: 1243303 (The Pile)

Max Activating Token Index: 161

Text #3

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3664. Min Act: -0.0000

Data Index: 707948 (The Pile)

Max Activating Token Index: 531

Text #4

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3352. Min Act: -0.0000

Data Index: 1659296 (The Pile)

Max Activating Token Index: 578

Text #5

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3410. Min Act: -0.0000

Data Index: 1873960 (The Pile)

Max Activating Token Index: 830

Text #6

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3050. Min Act: -0.0000

Data Index: 1653173 (The Pile)

Max Activating Token Index: 567

Text #7

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3321. Min Act: -0.0000

Data Index: 1114392 (The Pile)

Max Activating Token Index: 248

Text #8

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3010. Min Act: -0.0000

Data Index: 1752903 (The Pile)

Max Activating Token Index: 381

Text #9

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.2954. Min Act: -0.0000

Data Index: 1729792 (The Pile)

Max Activating Token Index: 349

Text #10

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3094. Min Act: -0.0000

Data Index: 1409674 (The Pile)

Max Activating Token Index: 110

Text #11

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.2948. Min Act: -0.0000

Data Index: 1802496 (The Pile)

Max Activating Token Index: 599

Text #12

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3069. Min Act: -0.0000

Data Index: 997469 (The Pile)

Max Activating Token Index: 865

Text #13

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.2846. Min Act: -0.0000

Data Index: 733719 (The Pile)

Max Activating Token Index: 633

Text #14

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.2592. Min Act: -0.0000

Data Index: 13277 (The Pile)

Max Activating Token Index: 621

Text #15

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.2756. Min Act: -0.0000

Data Index: 1853077 (The Pile)

Max Activating Token Index: 320

Text #16

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.2632. Min Act: -0.0000

Data Index: 1822884 (The Pile)

Max Activating Token Index: 735

Text #17

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.2629. Min Act: -0.0000

Data Index: 823006 (The Pile)

Max Activating Token Index: 241

Text #18

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.2826. Min Act: -0.0000

Data Index: 1230850 (The Pile)

Max Activating Token Index: 153

Text #19

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.2659. Min Act: -0.0000

Data Index: 328220 (The Pile)

Max Activating Token Index: 823