Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3394 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.2268. Min Act: -0.0002

Data Index: 975348 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.2235. Min Act: -0.0001

Data Index: 242291 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1958. Min Act: -0.0001

Data Index: 480442 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1737. Min Act: -0.0002

Data Index: 938059 (C4 (Web Text))

Max Activating Token Index: 329

Text #4

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.2029. Min Act: -0.0002

Data Index: 927098 (C4 (Web Text))

Max Activating Token Index: 11

Text #5

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1811. Min Act: -0.0002

Data Index: 1035978 (C4 (Web Text))

Max Activating Token Index: 208

Text #6

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1794. Min Act: -0.0002

Data Index: 823246 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1808. Min Act: -0.0002

Data Index: 78204 (C4 (Web Text))

Max Activating Token Index: 311

Text #8

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1737. Min Act: -0.0001

Data Index: 815351 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1729. Min Act: -0.0001

Data Index: 372967 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1787. Min Act: -0.0001

Data Index: 710586 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1724. Min Act: -0.0002

Data Index: 1182395 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1535. Min Act: -0.0002

Data Index: 108622 (C4 (Web Text))

Max Activating Token Index: 246

Text #13

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1700. Min Act: -0.0002

Data Index: 795867 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1653. Min Act: -0.0001

Data Index: 1158953 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1643. Min Act: -0.0002

Data Index: 1285266 (C4 (Web Text))

Max Activating Token Index: 361

Text #16

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1650. Min Act: -0.0001

Data Index: 1113188 (C4 (Web Text))

Max Activating Token Index: 202

Text #17

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1716. Min Act: -0.0002

Data Index: 827591 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1565. Min Act: -0.0001

Data Index: 183169 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 0.2268. Min Range: -0.2268

Max Act: 0.1591. Min Act: -0.0002

Data Index: 834845 (C4 (Web Text))

Max Activating Token Index: 218