Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 364 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.4774. Min Range: -1.4774

Max Act: 1.4774. Min Act: -0.0000

Data Index: 1246208 (C4 (Web Text))

Max Activating Token Index: 302

Text #1

Max Range: 1.4774. Min Range: -1.4774

Max Act: 1.4713. Min Act: -0.0000

Data Index: 746046 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 1.4774. Min Range: -1.4774

Max Act: 1.3060. Min Act: -0.0000

Data Index: 1127037 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 1.4774. Min Range: -1.4774

Max Act: 1.1865. Min Act: -0.0000

Data Index: 1634075 (Python Code)

Max Activating Token Index: 338

Text #4

Max Range: 1.4774. Min Range: -1.4774

Max Act: 1.1872. Min Act: -0.0000

Data Index: 1317519 (C4 (Web Text))

Max Activating Token Index: 366

Text #5

Max Range: 1.4774. Min Range: -1.4774

Max Act: 1.0999. Min Act: -0.0000

Data Index: 590799 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 1.4774. Min Range: -1.4774

Max Act: 1.0900. Min Act: -0.0000

Data Index: 1317524 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 1.4774. Min Range: -1.4774

Max Act: 1.0856. Min Act: -0.0000

Data Index: 1289747 (C4 (Web Text))

Max Activating Token Index: 922

Text #8

Max Range: 1.4774. Min Range: -1.4774

Max Act: 1.1139. Min Act: -0.0000

Data Index: 572045 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 1.4774. Min Range: -1.4774

Max Act: 1.1653. Min Act: -0.0000

Data Index: 1276026 (C4 (Web Text))

Max Activating Token Index: 819

Text #10

Max Range: 1.4774. Min Range: -1.4774

Max Act: 1.0680. Min Act: -0.0000

Data Index: 747254 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 1.4774. Min Range: -1.4774

Max Act: 1.0033. Min Act: -0.0000

Data Index: 1560195 (Python Code)

Max Activating Token Index: 766

Text #12

Max Range: 1.4774. Min Range: -1.4774

Max Act: 1.0575. Min Act: -0.0000

Data Index: 1433683 (Python Code)

Max Activating Token Index: 399

Text #13

Max Range: 1.4774. Min Range: -1.4774

Max Act: 1.0352. Min Act: -0.0000

Data Index: 1389326 (Python Code)

Max Activating Token Index: 882

Text #14

Max Range: 1.4774. Min Range: -1.4774

Max Act: 1.0611. Min Act: -0.0000

Data Index: 1423828 (Python Code)

Max Activating Token Index: 324

Text #15

Max Range: 1.4774. Min Range: -1.4774

Max Act: 1.0735. Min Act: -0.0000

Data Index: 995273 (C4 (Web Text))

Max Activating Token Index: 77

Text #16

Max Range: 1.4774. Min Range: -1.4774

Max Act: 1.0206. Min Act: -0.0000

Data Index: 1405558 (Python Code)

Max Activating Token Index: 187

Text #17

Max Range: 1.4774. Min Range: -1.4774

Max Act: 1.0329. Min Act: -0.0000

Data Index: 938486 (C4 (Web Text))

Max Activating Token Index: 45

Text #18

Max Range: 1.4774. Min Range: -1.4774

Max Act: 1.0300. Min Act: -0.0000

Data Index: 89124 (C4 (Web Text))

Max Activating Token Index: 301

Text #19

Max Range: 1.4774. Min Range: -1.4774

Max Act: 1.0516. Min Act: -0.0000

Data Index: 1389763 (Python Code)

Max Activating Token Index: 129