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

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

Neuron 2982 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.2304. Min Act: -0.0000

Data Index: 746683 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.2311. Min Act: -0.0000

Data Index: 423615 (C4 (Web Text))

Max Activating Token Index: 399

Text #2

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.2299. Min Act: -0.0000

Data Index: 968200 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.2013. Min Act: -0.0000

Data Index: 136419 (C4 (Web Text))

Max Activating Token Index: 783

Text #4

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.2249. Min Act: -0.0000

Data Index: 770612 (C4 (Web Text))

Max Activating Token Index: 895

Text #5

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.2105. Min Act: -0.0000

Data Index: 421757 (C4 (Web Text))

Max Activating Token Index: 271

Text #6

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1951. Min Act: -0.0000

Data Index: 773349 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.2123. Min Act: -0.0000

Data Index: 54785 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.2009. Min Act: -0.0000

Data Index: 1068915 (C4 (Web Text))

Max Activating Token Index: 324

Text #9

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1844. Min Act: -0.0000

Data Index: 574147 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1924. Min Act: -0.0000

Data Index: 1262086 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1902. Min Act: -0.0000

Data Index: 1110195 (C4 (Web Text))

Max Activating Token Index: 774

Text #12

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1829. Min Act: -0.0000

Data Index: 718194 (C4 (Web Text))

Max Activating Token Index: 319

Text #13

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1743. Min Act: -0.0000

Data Index: 862447 (C4 (Web Text))

Max Activating Token Index: 686

Text #14

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1743. Min Act: -0.0000

Data Index: 1261964 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1846. Min Act: -0.0000

Data Index: 1337533 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1836. Min Act: -0.0000

Data Index: 28026 (C4 (Web Text))

Max Activating Token Index: 518

Text #17

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1737. Min Act: -0.0000

Data Index: 637310 (C4 (Web Text))

Max Activating Token Index: 762

Text #18

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1739. Min Act: -0.0000

Data Index: 445865 (C4 (Web Text))

Max Activating Token Index: 996

Text #19

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1818. Min Act: -0.0000

Data Index: 46619 (C4 (Web Text))

Max Activating Token Index: 836