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

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

Neuron 327 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: 0.2506. Min Range: -0.2506

Max Act: 0.2506. Min Act: 0.0000

Data Index: 221913 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.2373. Min Act: 0.0000

Data Index: 1029115 (C4 (Web Text))

Max Activating Token Index: 397

Text #2

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.2206. Min Act: -0.0000

Data Index: 211025 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.2149. Min Act: -0.0000

Data Index: 530989 (C4 (Web Text))

Max Activating Token Index: 656

Text #4

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.2075. Min Act: 0.0000

Data Index: 801797 (C4 (Web Text))

Max Activating Token Index: 205

Text #5

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.2008. Min Act: 0.0000

Data Index: 349923 (C4 (Web Text))

Max Activating Token Index: 112

Text #6

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.2033. Min Act: -0.0000

Data Index: 470029 (C4 (Web Text))

Max Activating Token Index: 636

Text #7

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.1908. Min Act: -0.0000

Data Index: 377253 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.1960. Min Act: -0.0000

Data Index: 535451 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.1958. Min Act: -0.0000

Data Index: 297450 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.1924. Min Act: -0.0000

Data Index: 1010964 (C4 (Web Text))

Max Activating Token Index: 630

Text #11

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.1820. Min Act: -0.0000

Data Index: 1160276 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.1821. Min Act: -0.0000

Data Index: 887236 (C4 (Web Text))

Max Activating Token Index: 946

Text #13

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.1789. Min Act: -0.0000

Data Index: 46149 (C4 (Web Text))

Max Activating Token Index: 849

Text #14

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.1789. Min Act: -0.0000

Data Index: 1185190 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.1748. Min Act: -0.0000

Data Index: 785162 (C4 (Web Text))

Max Activating Token Index: 786

Text #16

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.1905. Min Act: -0.0000

Data Index: 383566 (C4 (Web Text))

Max Activating Token Index: 434

Text #17

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.1737. Min Act: 0.0000

Data Index: 134185 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.1729. Min Act: -0.0000

Data Index: 714254 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 0.2506. Min Range: -0.2506

Max Act: 0.1720. Min Act: -0.0000

Data Index: 54291 (C4 (Web Text))

Max Activating Token Index: 75