Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 774 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.2220. Min Act: -0.0001

Data Index: 256030 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.2046. Min Act: -0.0001

Data Index: 353678 (C4 (Web Text))

Max Activating Token Index: 910

Text #2

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1934. Min Act: -0.0001

Data Index: 254148 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1948. Min Act: -0.0001

Data Index: 263312 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1810. Min Act: -0.0001

Data Index: 952483 (C4 (Web Text))

Max Activating Token Index: 997

Text #5

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1871. Min Act: -0.0001

Data Index: 280249 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1836. Min Act: -0.0001

Data Index: 458472 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1776. Min Act: -0.0001

Data Index: 369463 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1745. Min Act: -0.0001

Data Index: 503318 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1862. Min Act: -0.0001

Data Index: 55048 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1860. Min Act: -0.0001

Data Index: 483859 (C4 (Web Text))

Max Activating Token Index: 462

Text #11

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1831. Min Act: -0.0001

Data Index: 447265 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1709. Min Act: -0.0001

Data Index: 1025769 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1814. Min Act: -0.0001

Data Index: 60672 (C4 (Web Text))

Max Activating Token Index: 252

Text #14

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1741. Min Act: -0.0001

Data Index: 58071 (C4 (Web Text))

Max Activating Token Index: 57

Text #15

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1705. Min Act: -0.0001

Data Index: 277793 (C4 (Web Text))

Max Activating Token Index: 209

Text #16

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1686. Min Act: -0.0001

Data Index: 1077036 (C4 (Web Text))

Max Activating Token Index: 517

Text #17

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1697. Min Act: -0.0001

Data Index: 424862 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1580. Min Act: -0.0001

Data Index: 343901 (C4 (Web Text))

Max Activating Token Index: 262

Text #19

Max Range: 0.2220. Min Range: -0.2220

Max Act: 0.1756. Min Act: -0.0001

Data Index: 1211142 (C4 (Web Text))

Max Activating Token Index: 744