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

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

Neuron 5215 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.2227. Min Act: -0.0000

Data Index: 963265 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.2136. Min Act: -0.0000

Data Index: 696262 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.2290. Min Act: -0.0000

Data Index: 777654 (C4 (Web Text))

Max Activating Token Index: 331

Text #3

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.2095. Min Act: -0.0000

Data Index: 1030133 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1960. Min Act: -0.0000

Data Index: 843494 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1990. Min Act: -0.0000

Data Index: 103437 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1900. Min Act: -0.0000

Data Index: 178812 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1806. Min Act: -0.0000

Data Index: 906917 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1857. Min Act: -0.0000

Data Index: 1066865 (C4 (Web Text))

Max Activating Token Index: 945

Text #9

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1907. Min Act: -0.0000

Data Index: 597691 (C4 (Web Text))

Max Activating Token Index: 67

Text #10

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1822. Min Act: -0.0000

Data Index: 954778 (C4 (Web Text))

Max Activating Token Index: 767

Text #11

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1817. Min Act: -0.0000

Data Index: 358843 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1695. Min Act: -0.0000

Data Index: 1146209 (C4 (Web Text))

Max Activating Token Index: 973

Text #13

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1845. Min Act: -0.0000

Data Index: 730413 (C4 (Web Text))

Max Activating Token Index: 438

Text #14

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1814. Min Act: -0.0000

Data Index: 223727 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1757. Min Act: -0.0000

Data Index: 146813 (C4 (Web Text))

Max Activating Token Index: 559

Text #16

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1731. Min Act: -0.0000

Data Index: 1084004 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1671. Min Act: -0.0000

Data Index: 128780 (C4 (Web Text))

Max Activating Token Index: 571

Text #18

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1671. Min Act: -0.0000

Data Index: 674717 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 0.2290. Min Range: -0.2290

Max Act: 0.1776. Min Act: -0.0000

Data Index: 749943 (C4 (Web Text))

Max Activating Token Index: 425