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

Dataset: The Pile

Neuron 3813 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.6460. Min Act: -0.0000

Data Index: 1069260 (The Pile)

Max Activating Token Index: 33

Text #1

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.6377. Min Act: -0.0000

Data Index: 248578 (The Pile)

Max Activating Token Index: 285

Text #2

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.6437. Min Act: -0.0000

Data Index: 925508 (The Pile)

Max Activating Token Index: 736

Text #3

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.6175. Min Act: 0.0000

Data Index: 776109 (The Pile)

Max Activating Token Index: 587

Text #4

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.6289. Min Act: -0.0000

Data Index: 401402 (The Pile)

Max Activating Token Index: 377

Text #5

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.5915. Min Act: -0.0000

Data Index: 1164227 (The Pile)

Max Activating Token Index: 71

Text #6

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.6370. Min Act: -0.0000

Data Index: 33297 (The Pile)

Max Activating Token Index: 399

Text #7

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.6028. Min Act: -0.0000

Data Index: 870294 (The Pile)

Max Activating Token Index: 282

Text #8

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.6173. Min Act: -0.0000

Data Index: 1527768 (The Pile)

Max Activating Token Index: 324

Text #9

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.5929. Min Act: -0.0000

Data Index: 742556 (The Pile)

Max Activating Token Index: 348

Text #10

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.5883. Min Act: -0.0000

Data Index: 1672801 (The Pile)

Max Activating Token Index: 249

Text #11

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.5791. Min Act: -0.0000

Data Index: 227098 (The Pile)

Max Activating Token Index: 29

Text #12

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.5576. Min Act: -0.0000

Data Index: 1797531 (The Pile)

Max Activating Token Index: 772

Text #13

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.5508. Min Act: -0.0000

Data Index: 1858118 (The Pile)

Max Activating Token Index: 893

Text #14

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.5709. Min Act: -0.0000

Data Index: 1044526 (The Pile)

Max Activating Token Index: 74

Text #15

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.5675. Min Act: -0.0000

Data Index: 1365051 (The Pile)

Max Activating Token Index: 107

Text #16

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.5409. Min Act: -0.0000

Data Index: 193054 (The Pile)

Max Activating Token Index: 51

Text #17

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.5547. Min Act: -0.0000

Data Index: 1992752 (The Pile)

Max Activating Token Index: 115

Text #18

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.5720. Min Act: -0.0000

Data Index: 1641788 (The Pile)

Max Activating Token Index: 442

Text #19

Max Range: 0.6460. Min Range: -0.6460

Max Act: 0.5515. Min Act: -0.0000

Data Index: 1326749 (The Pile)

Max Activating Token Index: 641