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

Dataset: The Pile

Neuron 3940 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: 0.2573. Min Range: -0.2573

Max Act: 0.2573. Min Act: -0.0000

Data Index: 1201668 (The Pile)

Max Activating Token Index: 761

Text #1

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.2302. Min Act: -0.0000

Data Index: 1619438 (The Pile)

Max Activating Token Index: 921

Text #2

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.2212. Min Act: -0.0000

Data Index: 1460961 (The Pile)

Max Activating Token Index: 517

Text #3

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.2136. Min Act: -0.0000

Data Index: 1243664 (The Pile)

Max Activating Token Index: 639

Text #4

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.2002. Min Act: -0.0000

Data Index: 591978 (The Pile)

Max Activating Token Index: 534

Text #5

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.2075. Min Act: -0.0000

Data Index: 1743626 (The Pile)

Max Activating Token Index: 1016

Text #6

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1961. Min Act: -0.0000

Data Index: 507818 (The Pile)

Max Activating Token Index: 979

Text #7

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1981. Min Act: -0.0000

Data Index: 136162 (The Pile)

Max Activating Token Index: 613

Text #8

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1768. Min Act: -0.0000

Data Index: 155627 (The Pile)

Max Activating Token Index: 860

Text #9

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1841. Min Act: -0.0000

Data Index: 206459 (The Pile)

Max Activating Token Index: 309

Text #10

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1919. Min Act: -0.0000

Data Index: 194441 (The Pile)

Max Activating Token Index: 289

Text #11

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1851. Min Act: -0.0000

Data Index: 1611712 (The Pile)

Max Activating Token Index: 230

Text #12

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1847. Min Act: -0.0000

Data Index: 814343 (The Pile)

Max Activating Token Index: 394

Text #13

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1671. Min Act: -0.0000

Data Index: 463488 (The Pile)

Max Activating Token Index: 149

Text #14

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1643. Min Act: -0.0000

Data Index: 1477369 (The Pile)

Max Activating Token Index: 22

Text #15

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1654. Min Act: -0.0000

Data Index: 1366734 (The Pile)

Max Activating Token Index: 425

Text #16

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1642. Min Act: -0.0000

Data Index: 282906 (The Pile)

Max Activating Token Index: 817

Text #17

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1660. Min Act: -0.0000

Data Index: 1257517 (The Pile)

Max Activating Token Index: 223

Text #18

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1509. Min Act: -0.0000

Data Index: 1207603 (The Pile)

Max Activating Token Index: 305

Text #19

Max Range: 0.2573. Min Range: -0.2573

Max Act: 0.1555. Min Act: -0.0000

Data Index: 718697 (The Pile)

Max Activating Token Index: 343