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

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

Neuron 5098 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.2188. Min Act: -0.0001

Data Index: 1620752 (Python Code)

Max Activating Token Index: 152

Text #1

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.2269. Min Act: -0.0001

Data Index: 574497 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.2074. Min Act: -0.0001

Data Index: 1209432 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.1932. Min Act: -0.0001

Data Index: 1487199 (Python Code)

Max Activating Token Index: 994

Text #4

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.2008. Min Act: -0.0001

Data Index: 1011819 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.1987. Min Act: -0.0001

Data Index: 28327 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.1890. Min Act: -0.0001

Data Index: 1467382 (Python Code)

Max Activating Token Index: 34

Text #7

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.1808. Min Act: -0.0001

Data Index: 1401573 (Python Code)

Max Activating Token Index: 566

Text #8

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.1867. Min Act: -0.0001

Data Index: 284182 (C4 (Web Text))

Max Activating Token Index: 2

Text #9

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.1916. Min Act: -0.0001

Data Index: 252131 (C4 (Web Text))

Max Activating Token Index: 685

Text #10

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.1816. Min Act: -0.0001

Data Index: 248714 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.1947. Min Act: -0.0001

Data Index: 1518639 (Python Code)

Max Activating Token Index: 695

Text #12

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.1879. Min Act: -0.0001

Data Index: 1171410 (C4 (Web Text))

Max Activating Token Index: 162

Text #13

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.1715. Min Act: -0.0001

Data Index: 1227300 (C4 (Web Text))

Max Activating Token Index: 303

Text #14

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.1749. Min Act: -0.0001

Data Index: 1475659 (Python Code)

Max Activating Token Index: 539

Text #15

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.1838. Min Act: -0.0001

Data Index: 379231 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.1691. Min Act: -0.0001

Data Index: 1523072 (Python Code)

Max Activating Token Index: 471

Text #17

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.1736. Min Act: -0.0001

Data Index: 717654 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.1678. Min Act: -0.0001

Data Index: 904645 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.2269. Min Range: -0.2269

Max Act: 0.1698. Min Act: -0.0001

Data Index: 1188448 (C4 (Web Text))

Max Activating Token Index: 594