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

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

Neuron 2722 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.2865. Min Act: -0.0003

Data Index: 47819 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.2445. Min Act: -0.0002

Data Index: 877908 (C4 (Web Text))

Max Activating Token Index: 863

Text #2

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.2250. Min Act: -0.0003

Data Index: 36331 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.2225. Min Act: -0.0003

Data Index: 583473 (C4 (Web Text))

Max Activating Token Index: 663

Text #4

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.2163. Min Act: -0.0003

Data Index: 914612 (C4 (Web Text))

Max Activating Token Index: 964

Text #5

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.2132. Min Act: -0.0002

Data Index: 672463 (C4 (Web Text))

Max Activating Token Index: 671

Text #6

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.2125. Min Act: -0.0003

Data Index: 190643 (C4 (Web Text))

Max Activating Token Index: 987

Text #7

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1940. Min Act: -0.0003

Data Index: 386642 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1902. Min Act: -0.0003

Data Index: 1093940 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1980. Min Act: -0.0003

Data Index: 465530 (C4 (Web Text))

Max Activating Token Index: 947

Text #10

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1906. Min Act: -0.0003

Data Index: 1127149 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1896. Min Act: -0.0003

Data Index: 851687 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1758. Min Act: -0.0002

Data Index: 296391 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1873. Min Act: -0.0003

Data Index: 1095420 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1836. Min Act: -0.0003

Data Index: 71178 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1770. Min Act: -0.0003

Data Index: 891319 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1770. Min Act: -0.0002

Data Index: 222568 (C4 (Web Text))

Max Activating Token Index: 807

Text #17

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1742. Min Act: -0.0003

Data Index: 410072 (C4 (Web Text))

Max Activating Token Index: 398

Text #18

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1730. Min Act: -0.0003

Data Index: 1306023 (C4 (Web Text))

Max Activating Token Index: 41

Text #19

Max Range: 0.2865. Min Range: -0.2865

Max Act: 0.1860. Min Act: -0.0002

Data Index: 648887 (C4 (Web Text))

Max Activating Token Index: 673