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

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

Neuron 951 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: 0.2044. Min Range: -0.2044

Max Act: 0.1912. Min Act: -0.0001

Data Index: 716330 (C4 (Web Text))

Max Activating Token Index: 71

Text #1

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.2044. Min Act: -0.0000

Data Index: 1215283 (C4 (Web Text))

Max Activating Token Index: 295

Text #2

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1753. Min Act: -0.0001

Data Index: 1220540 (C4 (Web Text))

Max Activating Token Index: 574

Text #3

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1712. Min Act: -0.0001

Data Index: 575404 (C4 (Web Text))

Max Activating Token Index: 836

Text #4

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1650. Min Act: -0.0000

Data Index: 621322 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1644. Min Act: -0.0001

Data Index: 529152 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1639. Min Act: -0.0000

Data Index: 131307 (C4 (Web Text))

Max Activating Token Index: 152

Text #7

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1696. Min Act: -0.0001

Data Index: 1391062 (Python Code)

Max Activating Token Index: 595

Text #8

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1695. Min Act: -0.0001

Data Index: 428910 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1663. Min Act: -0.0001

Data Index: 368541 (C4 (Web Text))

Max Activating Token Index: 441

Text #10

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1621. Min Act: -0.0000

Data Index: 905271 (C4 (Web Text))

Max Activating Token Index: 729

Text #11

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1626. Min Act: -0.0000

Data Index: 785056 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1434. Min Act: -0.0001

Data Index: 653729 (C4 (Web Text))

Max Activating Token Index: 981

Text #13

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1451. Min Act: -0.0001

Data Index: 243250 (C4 (Web Text))

Max Activating Token Index: 37

Text #14

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1501. Min Act: -0.0000

Data Index: 149220 (C4 (Web Text))

Max Activating Token Index: 152

Text #15

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1429. Min Act: -0.0001

Data Index: 386516 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1362. Min Act: -0.0000

Data Index: 845324 (C4 (Web Text))

Max Activating Token Index: 690

Text #17

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1432. Min Act: -0.0000

Data Index: 197523 (C4 (Web Text))

Max Activating Token Index: 272

Text #18

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1472. Min Act: -0.0001

Data Index: 1246182 (C4 (Web Text))

Max Activating Token Index: 311

Text #19

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1472. Min Act: -0.0001

Data Index: 293637 (C4 (Web Text))

Max Activating Token Index: 71