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

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

Neuron 3272 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: 0.1642. Min Range: -0.1642

Max Act: 0.1642. Min Act: -0.0001

Data Index: 552493 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1556. Min Act: -0.0002

Data Index: 748127 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1546. Min Act: -0.0002

Data Index: 657170 (C4 (Web Text))

Max Activating Token Index: 443

Text #3

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1594. Min Act: -0.0002

Data Index: 508990 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1489. Min Act: -0.0001

Data Index: 855265 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1531. Min Act: -0.0002

Data Index: 654437 (C4 (Web Text))

Max Activating Token Index: 996

Text #6

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1425. Min Act: -0.0001

Data Index: 344140 (C4 (Web Text))

Max Activating Token Index: 627

Text #7

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1573. Min Act: -0.0001

Data Index: 542317 (C4 (Web Text))

Max Activating Token Index: 915

Text #8

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1451. Min Act: -0.0002

Data Index: 318899 (C4 (Web Text))

Max Activating Token Index: 23

Text #9

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1401. Min Act: -0.0001

Data Index: 1220286 (C4 (Web Text))

Max Activating Token Index: 784

Text #10

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1405. Min Act: -0.0001

Data Index: 1060805 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1330. Min Act: -0.0001

Data Index: 1011897 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1370. Min Act: -0.0001

Data Index: 1133760 (C4 (Web Text))

Max Activating Token Index: 741

Text #13

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1431. Min Act: -0.0001

Data Index: 85498 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1360. Min Act: -0.0002

Data Index: 1268229 (C4 (Web Text))

Max Activating Token Index: 924

Text #15

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1465. Min Act: -0.0002

Data Index: 806619 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1518. Min Act: -0.0002

Data Index: 1005392 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1259. Min Act: -0.0002

Data Index: 490539 (C4 (Web Text))

Max Activating Token Index: 597

Text #18

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1389. Min Act: -0.0002

Data Index: 815729 (C4 (Web Text))

Max Activating Token Index: 553

Text #19

Max Range: 0.1642. Min Range: -0.1642

Max Act: 0.1414. Min Act: -0.0001

Data Index: 900806 (C4 (Web Text))

Max Activating Token Index: 285