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

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

Neuron 4678 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.2284. Min Act: -0.0000

Data Index: 1088873 (C4 (Web Text))

Max Activating Token Index: 955

Text #1

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.2234. Min Act: -0.0000

Data Index: 957786 (C4 (Web Text))

Max Activating Token Index: 363

Text #2

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.2160. Min Act: -0.0000

Data Index: 1037032 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.2064. Min Act: -0.0000

Data Index: 574593 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.1959. Min Act: -0.0000

Data Index: 551378 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.1939. Min Act: -0.0000

Data Index: 366470 (C4 (Web Text))

Max Activating Token Index: 986

Text #6

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.1891. Min Act: -0.0000

Data Index: 222169 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.1867. Min Act: -0.0000

Data Index: 1060015 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.1891. Min Act: -0.0000

Data Index: 149273 (C4 (Web Text))

Max Activating Token Index: 997

Text #9

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.1689. Min Act: -0.0000

Data Index: 642895 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.1801. Min Act: -0.0000

Data Index: 42604 (C4 (Web Text))

Max Activating Token Index: 271

Text #11

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.1785. Min Act: -0.0000

Data Index: 84647 (C4 (Web Text))

Max Activating Token Index: 31

Text #12

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.1751. Min Act: 0.0000

Data Index: 882674 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.1696. Min Act: -0.0000

Data Index: 984342 (C4 (Web Text))

Max Activating Token Index: 793

Text #14

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.1768. Min Act: -0.0000

Data Index: 365173 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.1716. Min Act: -0.0000

Data Index: 246620 (C4 (Web Text))

Max Activating Token Index: 266

Text #16

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.1758. Min Act: -0.0000

Data Index: 1141264 (C4 (Web Text))

Max Activating Token Index: 702

Text #17

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.1705. Min Act: -0.0000

Data Index: 15847 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.1688. Min Act: -0.0000

Data Index: 788829 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 0.2284. Min Range: -0.2284

Max Act: 0.1638. Min Act: -0.0000

Data Index: 979985 (C4 (Web Text))

Max Activating Token Index: 539