Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2015 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1661. Min Act: -0.0001

Data Index: 139895 (C4 (Web Text))

Max Activating Token Index: 750

Text #1

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1651. Min Act: -0.0001

Data Index: 1340592 (C4 (Web Text))

Max Activating Token Index: 282

Text #2

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1648. Min Act: -0.0001

Data Index: 930037 (C4 (Web Text))

Max Activating Token Index: 939

Text #3

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1560. Min Act: -0.0001

Data Index: 544863 (C4 (Web Text))

Max Activating Token Index: 629

Text #4

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1403. Min Act: -0.0001

Data Index: 507461 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1549. Min Act: -0.0001

Data Index: 660904 (C4 (Web Text))

Max Activating Token Index: 448

Text #6

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1420. Min Act: -0.0001

Data Index: 932168 (C4 (Web Text))

Max Activating Token Index: 613

Text #7

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1412. Min Act: -0.0001

Data Index: 54744 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1606. Min Act: -0.0001

Data Index: 572134 (C4 (Web Text))

Max Activating Token Index: 120

Text #9

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1476. Min Act: -0.0001

Data Index: 1058314 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1522. Min Act: -0.0001

Data Index: 667943 (C4 (Web Text))

Max Activating Token Index: 283

Text #11

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1493. Min Act: -0.0001

Data Index: 373207 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1402. Min Act: -0.0001

Data Index: 809608 (C4 (Web Text))

Max Activating Token Index: 123

Text #13

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1497. Min Act: -0.0001

Data Index: 373792 (C4 (Web Text))

Max Activating Token Index: 810

Text #14

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1461. Min Act: -0.0001

Data Index: 850225 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1388. Min Act: -0.0001

Data Index: 68162 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1363. Min Act: -0.0001

Data Index: 869678 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1447. Min Act: -0.0001

Data Index: 182310 (C4 (Web Text))

Max Activating Token Index: 334

Text #18

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1246. Min Act: -0.0001

Data Index: 874473 (C4 (Web Text))

Max Activating Token Index: 718

Text #19

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1307. Min Act: -0.0002

Data Index: 961318 (C4 (Web Text))

Max Activating Token Index: 376