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

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

Neuron 3720 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.2070. Min Act: -0.0001

Data Index: 150611 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1774. Min Act: -0.0001

Data Index: 628514 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1753. Min Act: -0.0001

Data Index: 18062 (C4 (Web Text))

Max Activating Token Index: 570

Text #3

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1750. Min Act: -0.0001

Data Index: 248875 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1859. Min Act: -0.0001

Data Index: 22096 (C4 (Web Text))

Max Activating Token Index: 98

Text #5

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1701. Min Act: -0.0000

Data Index: 686840 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1597. Min Act: -0.0000

Data Index: 174992 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1543. Min Act: -0.0001

Data Index: 707644 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1720. Min Act: -0.0001

Data Index: 1261493 (C4 (Web Text))

Max Activating Token Index: 1000

Text #9

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1576. Min Act: -0.0001

Data Index: 39269 (C4 (Web Text))

Max Activating Token Index: 525

Text #10

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1775. Min Act: -0.0001

Data Index: 224941 (C4 (Web Text))

Max Activating Token Index: 688

Text #11

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1514. Min Act: -0.0001

Data Index: 53119 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1399. Min Act: -0.0001

Data Index: 1204795 (C4 (Web Text))

Max Activating Token Index: 747

Text #13

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1473. Min Act: -0.0001

Data Index: 423215 (C4 (Web Text))

Max Activating Token Index: 315

Text #14

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1471. Min Act: -0.0001

Data Index: 190276 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1568. Min Act: -0.0001

Data Index: 1357156 (C4 (Web Text))

Max Activating Token Index: 422

Text #16

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1557. Min Act: -0.0001

Data Index: 909128 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1427. Min Act: -0.0001

Data Index: 1162154 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1433. Min Act: -0.0001

Data Index: 233500 (C4 (Web Text))

Max Activating Token Index: 735

Text #19

Max Range: 0.2070. Min Range: -0.2070

Max Act: 0.1380. Min Act: -0.0001

Data Index: 413977 (C4 (Web Text))

Max Activating Token Index: 551