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

Dataset: The Pile

Neuron 3359 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.3275. Min Act: -0.0000

Data Index: 1353958 (The Pile)

Max Activating Token Index: 196

Text #1

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2370. Min Act: -0.0000

Data Index: 1836214 (The Pile)

Max Activating Token Index: 325

Text #2

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.2390. Min Act: -0.0000

Data Index: 1035772 (The Pile)

Max Activating Token Index: 543

Text #3

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.1992. Min Act: -0.0000

Data Index: 1629302 (The Pile)

Max Activating Token Index: 84

Text #4

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.1858. Min Act: -0.0000

Data Index: 29049 (The Pile)

Max Activating Token Index: 667

Text #5

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.1811. Min Act: -0.0000

Data Index: 1665335 (The Pile)

Max Activating Token Index: 365

Text #6

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.1813. Min Act: -0.0000

Data Index: 1658389 (The Pile)

Max Activating Token Index: 340

Text #7

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.1839. Min Act: -0.0000

Data Index: 1359245 (The Pile)

Max Activating Token Index: 104

Text #8

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.1811. Min Act: -0.0000

Data Index: 1532983 (The Pile)

Max Activating Token Index: 24

Text #9

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.1637. Min Act: -0.0000

Data Index: 760300 (The Pile)

Max Activating Token Index: 151

Text #10

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.1855. Min Act: -0.0000

Data Index: 1308795 (The Pile)

Max Activating Token Index: 332

Text #11

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.1609. Min Act: -0.0000

Data Index: 44858 (The Pile)

Max Activating Token Index: 693

Text #12

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.1817. Min Act: -0.0000

Data Index: 1513932 (The Pile)

Max Activating Token Index: 629

Text #13

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.1592. Min Act: -0.0000

Data Index: 964250 (The Pile)

Max Activating Token Index: 935

Text #14

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.1623. Min Act: -0.0000

Data Index: 1628550 (The Pile)

Max Activating Token Index: 800

Text #15

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.1553. Min Act: -0.0000

Data Index: 1053057 (The Pile)

Max Activating Token Index: 376

Text #16

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.1556. Min Act: -0.0000

Data Index: 997940 (The Pile)

Max Activating Token Index: 445

Text #17

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.1588. Min Act: -0.0000

Data Index: 597653 (The Pile)

Max Activating Token Index: 980

Text #18

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.1472. Min Act: -0.0000

Data Index: 727968 (The Pile)

Max Activating Token Index: 596

Text #19

Max Range: 0.3275. Min Range: -0.3275

Max Act: 0.1572. Min Act: -0.0000

Data Index: 1083328 (The Pile)

Max Activating Token Index: 620