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

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

Neuron 2944 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1649. Min Act: -0.0000

Data Index: 1099693 (C4 (Web Text))

Max Activating Token Index: 105

Text #1

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1666. Min Act: -0.0001

Data Index: 865880 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1518. Min Act: -0.0001

Data Index: 1317821 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1548. Min Act: -0.0001

Data Index: 746410 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1407. Min Act: -0.0001

Data Index: 47450 (C4 (Web Text))

Max Activating Token Index: 350

Text #5

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1451. Min Act: -0.0001

Data Index: 990967 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1434. Min Act: -0.0000

Data Index: 1277663 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1389. Min Act: -0.0001

Data Index: 957611 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1369. Min Act: -0.0000

Data Index: 1310391 (C4 (Web Text))

Max Activating Token Index: 709

Text #9

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1405. Min Act: -0.0000

Data Index: 634012 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1404. Min Act: -0.0001

Data Index: 924386 (C4 (Web Text))

Max Activating Token Index: 43

Text #11

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1403. Min Act: -0.0001

Data Index: 539154 (C4 (Web Text))

Max Activating Token Index: 822

Text #12

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1280. Min Act: -0.0000

Data Index: 327996 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1371. Min Act: -0.0000

Data Index: 743839 (C4 (Web Text))

Max Activating Token Index: 718

Text #14

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1274. Min Act: -0.0001

Data Index: 456332 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1367. Min Act: -0.0000

Data Index: 693199 (C4 (Web Text))

Max Activating Token Index: 452

Text #16

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1361. Min Act: -0.0000

Data Index: 237436 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1219. Min Act: -0.0000

Data Index: 724881 (C4 (Web Text))

Max Activating Token Index: 186

Text #18

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1359. Min Act: -0.0001

Data Index: 1210214 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 0.1666. Min Range: -0.1666

Max Act: 0.1388. Min Act: -0.0001

Data Index: 1312915 (C4 (Web Text))

Max Activating Token Index: 782