Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1903 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1744. Min Act: -0.0001

Data Index: 122325 (C4 (Web Text))

Max Activating Token Index: 177

Text #1

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1496. Min Act: -0.0001

Data Index: 373086 (C4 (Web Text))

Max Activating Token Index: 269

Text #2

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1722. Min Act: -0.0001

Data Index: 415610 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1658. Min Act: -0.0001

Data Index: 754448 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1526. Min Act: -0.0001

Data Index: 50478 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1633. Min Act: -0.0001

Data Index: 1269081 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1526. Min Act: -0.0001

Data Index: 1202071 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1533. Min Act: -0.0001

Data Index: 1284275 (C4 (Web Text))

Max Activating Token Index: 32

Text #8

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1483. Min Act: -0.0001

Data Index: 1160032 (C4 (Web Text))

Max Activating Token Index: 577

Text #9

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1361. Min Act: -0.0001

Data Index: 513380 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1360. Min Act: -0.0001

Data Index: 655385 (C4 (Web Text))

Max Activating Token Index: 76

Text #11

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1388. Min Act: -0.0001

Data Index: 702719 (C4 (Web Text))

Max Activating Token Index: 159

Text #12

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1382. Min Act: -0.0001

Data Index: 451230 (C4 (Web Text))

Max Activating Token Index: 620

Text #13

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1469. Min Act: -0.0001

Data Index: 437059 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1408. Min Act: -0.0001

Data Index: 559135 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1261. Min Act: -0.0001

Data Index: 888325 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1335. Min Act: -0.0001

Data Index: 916101 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1333. Min Act: -0.0001

Data Index: 705544 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1375. Min Act: -0.0001

Data Index: 789750 (C4 (Web Text))

Max Activating Token Index: 983

Text #19

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1366. Min Act: -0.0001

Data Index: 679088 (C4 (Web Text))

Max Activating Token Index: 142