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

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

Neuron 2672 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: 0.2339. Min Range: -0.2339

Max Act: 0.2339. Min Act: -0.0000

Data Index: 162171 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1910. Min Act: -0.0000

Data Index: 1352779 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.2064. Min Act: -0.0000

Data Index: 1322857 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1992. Min Act: -0.0000

Data Index: 152581 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1893. Min Act: -0.0000

Data Index: 1116955 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1898. Min Act: -0.0000

Data Index: 938744 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.2022. Min Act: -0.0000

Data Index: 552455 (C4 (Web Text))

Max Activating Token Index: 926

Text #7

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1855. Min Act: -0.0000

Data Index: 377939 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.2045. Min Act: -0.0000

Data Index: 338503 (C4 (Web Text))

Max Activating Token Index: 950

Text #9

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1832. Min Act: -0.0000

Data Index: 33994 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1584. Min Act: -0.0000

Data Index: 1636472 (Python Code)

Max Activating Token Index: 870

Text #11

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1584. Min Act: -0.0001

Data Index: 1396435 (Python Code)

Max Activating Token Index: 717

Text #12

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1846. Min Act: -0.0000

Data Index: 1314777 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1636. Min Act: -0.0000

Data Index: 1067603 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1675. Min Act: -0.0000

Data Index: 364576 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1666. Min Act: -0.0000

Data Index: 309642 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1649. Min Act: -0.0000

Data Index: 559836 (C4 (Web Text))

Max Activating Token Index: 327

Text #17

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1635. Min Act: -0.0000

Data Index: 1634869 (Python Code)

Max Activating Token Index: 465

Text #18

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1682. Min Act: -0.0000

Data Index: 1229151 (C4 (Web Text))

Max Activating Token Index: 551

Text #19

Max Range: 0.2339. Min Range: -0.2339

Max Act: 0.1718. Min Act: -0.0000

Data Index: 756078 (C4 (Web Text))

Max Activating Token Index: 992