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

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

Neuron 493 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: 0.1821. Min Range: -0.1821

Max Act: 0.1821. Min Act: -0.0001

Data Index: 62626 (C4 (Web Text))

Max Activating Token Index: 143

Text #1

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1814. Min Act: -0.0001

Data Index: 245017 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1805. Min Act: -0.0001

Data Index: 359448 (C4 (Web Text))

Max Activating Token Index: 958

Text #3

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1738. Min Act: -0.0001

Data Index: 900892 (C4 (Web Text))

Max Activating Token Index: 126

Text #4

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1730. Min Act: -0.0001

Data Index: 203906 (C4 (Web Text))

Max Activating Token Index: 577

Text #5

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1694. Min Act: -0.0001

Data Index: 1065470 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1665. Min Act: -0.0001

Data Index: 1302523 (C4 (Web Text))

Max Activating Token Index: 860

Text #7

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1670. Min Act: -0.0001

Data Index: 305435 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1581. Min Act: -0.0001

Data Index: 991128 (C4 (Web Text))

Max Activating Token Index: 787

Text #9

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1569. Min Act: -0.0001

Data Index: 984932 (C4 (Web Text))

Max Activating Token Index: 316

Text #10

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1607. Min Act: -0.0001

Data Index: 1302925 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1593. Min Act: -0.0001

Data Index: 939510 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1537. Min Act: -0.0001

Data Index: 1333081 (C4 (Web Text))

Max Activating Token Index: 669

Text #13

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1594. Min Act: -0.0001

Data Index: 781582 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1635. Min Act: -0.0001

Data Index: 1343355 (C4 (Web Text))

Max Activating Token Index: 660

Text #15

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1468. Min Act: -0.0001

Data Index: 16318 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1632. Min Act: -0.0001

Data Index: 378376 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1623. Min Act: -0.0001

Data Index: 728850 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1566. Min Act: -0.0001

Data Index: 915127 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1676. Min Act: -0.0001

Data Index: 1158933 (C4 (Web Text))

Max Activating Token Index: 21