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

Dataset: The Pile

Neuron 1279 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5640. Min Range: -5.5640

Max Act: 5.5640. Min Act: -0.0000

Data Index: 1796051 (The Pile)

Max Activating Token Index: 436

Text #1

Max Range: 5.5640. Min Range: -5.5640

Max Act: 5.4267. Min Act: -0.0001

Data Index: 1512755 (The Pile)

Max Activating Token Index: 370

Text #2

Max Range: 5.5640. Min Range: -5.5640

Max Act: 5.1270. Min Act: -0.0000

Data Index: 1964230 (The Pile)

Max Activating Token Index: 458

Text #3

Max Range: 5.5640. Min Range: -5.5640

Max Act: 5.0085. Min Act: -0.0000

Data Index: 996148 (The Pile)

Max Activating Token Index: 524

Text #4

Max Range: 5.5640. Min Range: -5.5640

Max Act: 5.1674. Min Act: -0.0000

Data Index: 56201 (The Pile)

Max Activating Token Index: 137

Text #5

Max Range: 5.5640. Min Range: -5.5640

Max Act: 4.5491. Min Act: -0.0001

Data Index: 108228 (The Pile)

Max Activating Token Index: 124

Text #6

Max Range: 5.5640. Min Range: -5.5640

Max Act: 4.4336. Min Act: -0.0001

Data Index: 1452201 (The Pile)

Max Activating Token Index: 344

Text #7

Max Range: 5.5640. Min Range: -5.5640

Max Act: 4.6767. Min Act: -0.0000

Data Index: 789531 (The Pile)

Max Activating Token Index: 976

Text #8

Max Range: 5.5640. Min Range: -5.5640

Max Act: 4.4534. Min Act: -0.0000

Data Index: 719479 (The Pile)

Max Activating Token Index: 475

Text #9

Max Range: 5.5640. Min Range: -5.5640

Max Act: 4.1082. Min Act: -0.0001

Data Index: 721035 (The Pile)

Max Activating Token Index: 631

Text #10

Max Range: 5.5640. Min Range: -5.5640

Max Act: 4.3753. Min Act: -0.0000

Data Index: 19092 (The Pile)

Max Activating Token Index: 448

Text #11

Max Range: 5.5640. Min Range: -5.5640

Max Act: 4.4856. Min Act: -0.0000

Data Index: 324870 (The Pile)

Max Activating Token Index: 889

Text #12

Max Range: 5.5640. Min Range: -5.5640

Max Act: 4.2516. Min Act: -0.0000

Data Index: 1712408 (The Pile)

Max Activating Token Index: 596

Text #13

Max Range: 5.5640. Min Range: -5.5640

Max Act: 4.0175. Min Act: -0.0000

Data Index: 1023416 (The Pile)

Max Activating Token Index: 567

Text #14

Max Range: 5.5640. Min Range: -5.5640

Max Act: 3.8926. Min Act: -0.0000

Data Index: 841477 (The Pile)

Max Activating Token Index: 119

Text #15

Max Range: 5.5640. Min Range: -5.5640

Max Act: 4.2747. Min Act: -0.0000

Data Index: 352966 (The Pile)

Max Activating Token Index: 200

Text #16

Max Range: 5.5640. Min Range: -5.5640

Max Act: 4.3708. Min Act: -0.0000

Data Index: 478018 (The Pile)

Max Activating Token Index: 416

Text #17

Max Range: 5.5640. Min Range: -5.5640

Max Act: 3.7848. Min Act: -0.0000

Data Index: 1268267 (The Pile)

Max Activating Token Index: 583

Text #18

Max Range: 5.5640. Min Range: -5.5640

Max Act: 3.7425. Min Act: -0.0000

Data Index: 1336523 (The Pile)

Max Activating Token Index: 807

Text #19

Max Range: 5.5640. Min Range: -5.5640

Max Act: 3.6642. Min Act: -0.0000

Data Index: 200771 (The Pile)

Max Activating Token Index: 959