Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3106 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.4897. Min Act: -0.0000

Data Index: 292855 (The Pile)

Max Activating Token Index: 968

Text #1

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.5095. Min Act: -0.0000

Data Index: 1190894 (The Pile)

Max Activating Token Index: 1004

Text #2

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.4485. Min Act: -0.0000

Data Index: 581740 (The Pile)

Max Activating Token Index: 326

Text #3

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.4178. Min Act: -0.0000

Data Index: 174946 (The Pile)

Max Activating Token Index: 175

Text #4

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.4166. Min Act: -0.0000

Data Index: 345907 (The Pile)

Max Activating Token Index: 314

Text #5

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.3899. Min Act: -0.0000

Data Index: 171355 (The Pile)

Max Activating Token Index: 666

Text #6

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.4129. Min Act: -0.0000

Data Index: 1179389 (The Pile)

Max Activating Token Index: 877

Text #7

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.4019. Min Act: -0.0000

Data Index: 1808201 (The Pile)

Max Activating Token Index: 848

Text #8

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.4024. Min Act: -0.0000

Data Index: 1678478 (The Pile)

Max Activating Token Index: 415

Text #9

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.4042. Min Act: -0.0000

Data Index: 610939 (The Pile)

Max Activating Token Index: 301

Text #10

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.3819. Min Act: -0.0000

Data Index: 88872 (The Pile)

Max Activating Token Index: 687

Text #11

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.4019. Min Act: -0.0000

Data Index: 848933 (The Pile)

Max Activating Token Index: 189

Text #12

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.3931. Min Act: -0.0000

Data Index: 1671395 (The Pile)

Max Activating Token Index: 382

Text #13

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.3848. Min Act: -0.0000

Data Index: 1192402 (The Pile)

Max Activating Token Index: 594

Text #14

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.4063. Min Act: -0.0000

Data Index: 827430 (The Pile)

Max Activating Token Index: 829

Text #15

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.3695. Min Act: -0.0000

Data Index: 1557136 (The Pile)

Max Activating Token Index: 470

Text #16

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.3608. Min Act: -0.0000

Data Index: 503194 (The Pile)

Max Activating Token Index: 688

Text #17

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.3585. Min Act: -0.0000

Data Index: 60965 (The Pile)

Max Activating Token Index: 553

Text #18

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.3542. Min Act: -0.0000

Data Index: 67006 (The Pile)

Max Activating Token Index: 170

Text #19

Max Range: 0.5095. Min Range: -0.5095

Max Act: 0.3602. Min Act: -0.0000

Data Index: 780017 (The Pile)

Max Activating Token Index: 906