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

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

Neuron 1398 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.2222. Min Act: -0.0001

Data Index: 1655192 (Python Code)

Max Activating Token Index: 487

Text #1

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.2043. Min Act: -0.0001

Data Index: 1650114 (Python Code)

Max Activating Token Index: 642

Text #2

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.2033. Min Act: -0.0001

Data Index: 1363298 (Python Code)

Max Activating Token Index: 240

Text #3

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.2022. Min Act: -0.0001

Data Index: 1491286 (Python Code)

Max Activating Token Index: 227

Text #4

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.2094. Min Act: -0.0001

Data Index: 1618205 (Python Code)

Max Activating Token Index: 401

Text #5

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.1972. Min Act: -0.0001

Data Index: 1444871 (Python Code)

Max Activating Token Index: 138

Text #6

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.1921. Min Act: -0.0001

Data Index: 1470865 (Python Code)

Max Activating Token Index: 674

Text #7

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.1815. Min Act: -0.0001

Data Index: 1475553 (Python Code)

Max Activating Token Index: 206

Text #8

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.2030. Min Act: -0.0001

Data Index: 1601707 (Python Code)

Max Activating Token Index: 787

Text #9

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.1937. Min Act: -0.0001

Data Index: 169111 (C4 (Web Text))

Max Activating Token Index: 773

Text #10

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.1727. Min Act: -0.0001

Data Index: 676967 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.1850. Min Act: -0.0001

Data Index: 1557067 (Python Code)

Max Activating Token Index: 543

Text #12

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.1894. Min Act: -0.0001

Data Index: 1656830 (Python Code)

Max Activating Token Index: 595

Text #13

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.1709. Min Act: -0.0001

Data Index: 1573140 (Python Code)

Max Activating Token Index: 492

Text #14

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.1722. Min Act: -0.0001

Data Index: 1532149 (Python Code)

Max Activating Token Index: 125

Text #15

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.1733. Min Act: -0.0001

Data Index: 1615988 (Python Code)

Max Activating Token Index: 566

Text #16

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.1692. Min Act: -0.0001

Data Index: 1636684 (Python Code)

Max Activating Token Index: 246

Text #17

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.1643. Min Act: -0.0001

Data Index: 1466693 (Python Code)

Max Activating Token Index: 102

Text #18

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.1419. Min Act: -0.0001

Data Index: 1515994 (Python Code)

Max Activating Token Index: 118

Text #19

Max Range: 0.2222. Min Range: -0.2222

Max Act: 0.1575. Min Act: -0.0001

Data Index: 20113 (C4 (Web Text))

Max Activating Token Index: 452