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

Dataset: The Pile

Neuron 417 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: 0.8730. Min Range: -0.8730

Max Act: 0.8730. Min Act: -0.0000

Data Index: 855768 (The Pile)

Max Activating Token Index: 205

Text #1

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.8389. Min Act: -0.0000

Data Index: 1617816 (The Pile)

Max Activating Token Index: 702

Text #2

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.8154. Min Act: -0.0000

Data Index: 1738553 (The Pile)

Max Activating Token Index: 286

Text #3

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.8192. Min Act: -0.0000

Data Index: 1586608 (The Pile)

Max Activating Token Index: 79

Text #4

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.8210. Min Act: -0.0000

Data Index: 1388050 (The Pile)

Max Activating Token Index: 479

Text #5

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.7932. Min Act: -0.0000

Data Index: 403431 (The Pile)

Max Activating Token Index: 664

Text #6

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.7928. Min Act: -0.0000

Data Index: 1744634 (The Pile)

Max Activating Token Index: 122

Text #7

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.7910. Min Act: -0.0000

Data Index: 1155984 (The Pile)

Max Activating Token Index: 111

Text #8

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.7824. Min Act: -0.0000

Data Index: 1269945 (The Pile)

Max Activating Token Index: 583

Text #9

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.7762. Min Act: -0.0000

Data Index: 135944 (The Pile)

Max Activating Token Index: 81

Text #10

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.7818. Min Act: -0.0000

Data Index: 851600 (The Pile)

Max Activating Token Index: 81

Text #11

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.7816. Min Act: -0.0000

Data Index: 976830 (The Pile)

Max Activating Token Index: 224

Text #12

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.7552. Min Act: -0.0000

Data Index: 1922966 (The Pile)

Max Activating Token Index: 344

Text #13

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.7722. Min Act: -0.0000

Data Index: 260160 (The Pile)

Max Activating Token Index: 647

Text #14

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.7660. Min Act: -0.0000

Data Index: 19196 (The Pile)

Max Activating Token Index: 101

Text #15

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.7641. Min Act: -0.0000

Data Index: 490651 (The Pile)

Max Activating Token Index: 659

Text #16

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.7271. Min Act: -0.0000

Data Index: 395013 (The Pile)

Max Activating Token Index: 599

Text #17

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.7308. Min Act: -0.0000

Data Index: 1044359 (The Pile)

Max Activating Token Index: 327

Text #18

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.7543. Min Act: -0.0000

Data Index: 1757688 (The Pile)

Max Activating Token Index: 595

Text #19

Max Range: 0.8730. Min Range: -0.8730

Max Act: 0.7231. Min Act: -0.0000

Data Index: 1769919 (The Pile)

Max Activating Token Index: 514