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

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

Neuron 1902 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: 1.4807. Min Range: -1.4807

Max Act: 1.3892. Min Act: -0.0001

Data Index: 1246273 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 1.4807. Min Range: -1.4807

Max Act: 1.4807. Min Act: -0.0001

Data Index: 803884 (C4 (Web Text))

Max Activating Token Index: 82

Text #2

Max Range: 1.4807. Min Range: -1.4807

Max Act: 1.2739. Min Act: -0.0001

Data Index: 593051 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 1.4807. Min Range: -1.4807

Max Act: 1.2181. Min Act: -0.0002

Data Index: 649708 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 1.4807. Min Range: -1.4807

Max Act: 1.2536. Min Act: -0.0002

Data Index: 871780 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 1.4807. Min Range: -1.4807

Max Act: 1.2658. Min Act: -0.0001

Data Index: 1208992 (C4 (Web Text))

Max Activating Token Index: 193

Text #6

Max Range: 1.4807. Min Range: -1.4807

Max Act: 1.1678. Min Act: -0.0001

Data Index: 1293766 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 1.4807. Min Range: -1.4807

Max Act: 1.1961. Min Act: -0.0001

Data Index: 513738 (C4 (Web Text))

Max Activating Token Index: 122

Text #8

Max Range: 1.4807. Min Range: -1.4807

Max Act: 1.1566. Min Act: -0.0002

Data Index: 1356832 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 1.4807. Min Range: -1.4807

Max Act: 1.1743. Min Act: -0.0001

Data Index: 1059476 (C4 (Web Text))

Max Activating Token Index: 801

Text #10

Max Range: 1.4807. Min Range: -1.4807

Max Act: 1.1542. Min Act: -0.0001

Data Index: 66894 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 1.4807. Min Range: -1.4807

Max Act: 1.1068. Min Act: -0.0001

Data Index: 968505 (C4 (Web Text))

Max Activating Token Index: 630

Text #12

Max Range: 1.4807. Min Range: -1.4807

Max Act: 1.0893. Min Act: -0.0001

Data Index: 801415 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 1.4807. Min Range: -1.4807

Max Act: 1.0434. Min Act: -0.0002

Data Index: 801259 (C4 (Web Text))

Max Activating Token Index: 984

Text #14

Max Range: 1.4807. Min Range: -1.4807

Max Act: 1.1651. Min Act: -0.0002

Data Index: 1207739 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 1.4807. Min Range: -1.4807

Max Act: 1.1441. Min Act: -0.0001

Data Index: 219411 (C4 (Web Text))

Max Activating Token Index: 166

Text #16

Max Range: 1.4807. Min Range: -1.4807

Max Act: 1.0449. Min Act: -0.0002

Data Index: 322919 (C4 (Web Text))

Max Activating Token Index: 761

Text #17

Max Range: 1.4807. Min Range: -1.4807

Max Act: 1.0492. Min Act: -0.0001

Data Index: 1348002 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 1.4807. Min Range: -1.4807

Max Act: 1.0550. Min Act: -0.0001

Data Index: 1054759 (C4 (Web Text))

Max Activating Token Index: 710

Text #19

Max Range: 1.4807. Min Range: -1.4807

Max Act: 0.9699. Min Act: -0.0001

Data Index: 1224768 (C4 (Web Text))

Max Activating Token Index: 825