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

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

Neuron 1856 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1861. Min Act: -0.0001

Data Index: 482842 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1708. Min Act: -0.0001

Data Index: 495971 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1730. Min Act: -0.0001

Data Index: 1185142 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1928. Min Act: -0.0002

Data Index: 13342 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1709. Min Act: -0.0002

Data Index: 479062 (C4 (Web Text))

Max Activating Token Index: 946

Text #5

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1726. Min Act: -0.0001

Data Index: 1222789 (C4 (Web Text))

Max Activating Token Index: 759

Text #6

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1856. Min Act: -0.0002

Data Index: 768604 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1742. Min Act: -0.0001

Data Index: 217679 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1707. Min Act: -0.0001

Data Index: 386635 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1661. Min Act: -0.0002

Data Index: 476003 (C4 (Web Text))

Max Activating Token Index: 718

Text #10

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1724. Min Act: -0.0002

Data Index: 1194231 (C4 (Web Text))

Max Activating Token Index: 384

Text #11

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1602. Min Act: -0.0002

Data Index: 1036000 (C4 (Web Text))

Max Activating Token Index: 798

Text #12

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1693. Min Act: -0.0002

Data Index: 1019331 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1612. Min Act: -0.0002

Data Index: 459204 (C4 (Web Text))

Max Activating Token Index: 375

Text #14

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1680. Min Act: -0.0002

Data Index: 593662 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1634. Min Act: -0.0002

Data Index: 1023371 (C4 (Web Text))

Max Activating Token Index: 1022

Text #16

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1667. Min Act: -0.0001

Data Index: 729135 (C4 (Web Text))

Max Activating Token Index: 251

Text #17

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1602. Min Act: -0.0001

Data Index: 770942 (C4 (Web Text))

Max Activating Token Index: 385

Text #18

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1626. Min Act: -0.0001

Data Index: 279196 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 0.1928. Min Range: -0.1928

Max Act: 0.1563. Min Act: -0.0002

Data Index: 384526 (C4 (Web Text))

Max Activating Token Index: 878