Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4908 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1602. Min Act: -0.0002

Data Index: 636671 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1847. Min Act: -0.0002

Data Index: 1219444 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1703. Min Act: -0.0002

Data Index: 236750 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1422. Min Act: -0.0002

Data Index: 120339 (C4 (Web Text))

Max Activating Token Index: 767

Text #4

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1502. Min Act: -0.0002

Data Index: 675500 (C4 (Web Text))

Max Activating Token Index: 360

Text #5

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1376. Min Act: -0.0002

Data Index: 929908 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1473. Min Act: -0.0002

Data Index: 142408 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1520. Min Act: -0.0002

Data Index: 322680 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1438. Min Act: -0.0002

Data Index: 321418 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1407. Min Act: -0.0002

Data Index: 1326914 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1348. Min Act: -0.0002

Data Index: 728701 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1327. Min Act: -0.0002

Data Index: 642242 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1323. Min Act: -0.0002

Data Index: 1254649 (C4 (Web Text))

Max Activating Token Index: 449

Text #13

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1276. Min Act: -0.0002

Data Index: 953012 (C4 (Web Text))

Max Activating Token Index: 749

Text #14

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1291. Min Act: -0.0002

Data Index: 1193612 (C4 (Web Text))

Max Activating Token Index: 879

Text #15

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1230. Min Act: -0.0002

Data Index: 1255412 (C4 (Web Text))

Max Activating Token Index: 706

Text #16

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1322. Min Act: -0.0002

Data Index: 352699 (C4 (Web Text))

Max Activating Token Index: 961

Text #17

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1253. Min Act: -0.0002

Data Index: 884228 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1295. Min Act: -0.0002

Data Index: 472861 (C4 (Web Text))

Max Activating Token Index: 514

Text #19

Max Range: 0.1847. Min Range: -0.1847

Max Act: 0.1226. Min Act: -0.0002

Data Index: 243151 (C4 (Web Text))

Max Activating Token Index: 398