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

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

Neuron 2880 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: 0.1835. Min Range: -0.1835

Max Act: 0.1835. Min Act: -0.0001

Data Index: 745352 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1793. Min Act: -0.0001

Data Index: 1040103 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1765. Min Act: -0.0002

Data Index: 532476 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1804. Min Act: -0.0002

Data Index: 1245863 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1702. Min Act: -0.0002

Data Index: 1118716 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1685. Min Act: -0.0001

Data Index: 912416 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1718. Min Act: -0.0002

Data Index: 1156143 (C4 (Web Text))

Max Activating Token Index: 940

Text #7

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1714. Min Act: -0.0001

Data Index: 1088881 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1660. Min Act: -0.0001

Data Index: 49364 (C4 (Web Text))

Max Activating Token Index: 533

Text #9

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1574. Min Act: -0.0002

Data Index: 843284 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1523. Min Act: -0.0001

Data Index: 479590 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1488. Min Act: -0.0001

Data Index: 963992 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1541. Min Act: -0.0001

Data Index: 994044 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1458. Min Act: -0.0002

Data Index: 1062568 (C4 (Web Text))

Max Activating Token Index: 963

Text #14

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1424. Min Act: -0.0001

Data Index: 340349 (C4 (Web Text))

Max Activating Token Index: 216

Text #15

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1386. Min Act: -0.0002

Data Index: 253321 (C4 (Web Text))

Max Activating Token Index: 626

Text #16

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1431. Min Act: -0.0002

Data Index: 1028793 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1464. Min Act: -0.0002

Data Index: 1146904 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1420. Min Act: -0.0001

Data Index: 1205818 (C4 (Web Text))

Max Activating Token Index: 810

Text #19

Max Range: 0.1835. Min Range: -0.1835

Max Act: 0.1446. Min Act: -0.0002

Data Index: 1103779 (C4 (Web Text))

Max Activating Token Index: 838