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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5100 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.2322. Min Act: -0.0000

Data Index: 152833 (C4 (Web Text))

Max Activating Token Index: 369

Text #1

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.2214. Min Act: -0.0000

Data Index: 305111 (C4 (Web Text))

Max Activating Token Index: 1015

Text #2

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1931. Min Act: -0.0000

Data Index: 773426 (C4 (Web Text))

Max Activating Token Index: 639

Text #3

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1981. Min Act: -0.0000

Data Index: 982822 (C4 (Web Text))

Max Activating Token Index: 372

Text #4

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1971. Min Act: -0.0000

Data Index: 838181 (C4 (Web Text))

Max Activating Token Index: 701

Text #5

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1950. Min Act: -0.0000

Data Index: 996167 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1897. Min Act: -0.0000

Data Index: 1111909 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1923. Min Act: -0.0000

Data Index: 414413 (C4 (Web Text))

Max Activating Token Index: 27

Text #8

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1847. Min Act: -0.0000

Data Index: 1147739 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1943. Min Act: -0.0000

Data Index: 53448 (C4 (Web Text))

Max Activating Token Index: 708

Text #10

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1827. Min Act: -0.0000

Data Index: 1061350 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1876. Min Act: -0.0000

Data Index: 529069 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1809. Min Act: -0.0000

Data Index: 725405 (C4 (Web Text))

Max Activating Token Index: 781

Text #13

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1847. Min Act: -0.0000

Data Index: 157299 (C4 (Web Text))

Max Activating Token Index: 306

Text #14

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1852. Min Act: -0.0000

Data Index: 638754 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1833. Min Act: -0.0000

Data Index: 1068235 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1822. Min Act: 0.0000

Data Index: 116517 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1871. Min Act: -0.0000

Data Index: 228727 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1867. Min Act: -0.0000

Data Index: 613383 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 0.2322. Min Range: -0.2322

Max Act: 0.1806. Min Act: -0.0000

Data Index: 528814 (C4 (Web Text))

Max Activating Token Index: 601