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

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

Neuron 3976 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: 0.1971. Min Range: -0.1971

Max Act: 0.1882. Min Act: -0.0001

Data Index: 1517197 (Python Code)

Max Activating Token Index: 264

Text #1

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1971. Min Act: -0.0001

Data Index: 1502381 (Python Code)

Max Activating Token Index: 329

Text #2

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1771. Min Act: -0.0001

Data Index: 1615378 (Python Code)

Max Activating Token Index: 450

Text #3

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1741. Min Act: -0.0001

Data Index: 1376014 (Python Code)

Max Activating Token Index: 521

Text #4

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1684. Min Act: -0.0001

Data Index: 1442480 (Python Code)

Max Activating Token Index: 447

Text #5

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1715. Min Act: -0.0001

Data Index: 1597980 (Python Code)

Max Activating Token Index: 208

Text #6

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1658. Min Act: -0.0001

Data Index: 1500767 (Python Code)

Max Activating Token Index: 79

Text #7

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1692. Min Act: -0.0001

Data Index: 1642565 (Python Code)

Max Activating Token Index: 147

Text #8

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1465. Min Act: -0.0001

Data Index: 1604103 (Python Code)

Max Activating Token Index: 699

Text #9

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1679. Min Act: -0.0001

Data Index: 1453516 (Python Code)

Max Activating Token Index: 67

Text #10

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1544. Min Act: -0.0001

Data Index: 1382725 (Python Code)

Max Activating Token Index: 155

Text #11

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1694. Min Act: -0.0001

Data Index: 1548157 (Python Code)

Max Activating Token Index: 341

Text #12

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1529. Min Act: -0.0001

Data Index: 1573204 (Python Code)

Max Activating Token Index: 349

Text #13

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1616. Min Act: -0.0001

Data Index: 1430378 (Python Code)

Max Activating Token Index: 501

Text #14

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1608. Min Act: -0.0001

Data Index: 1461002 (Python Code)

Max Activating Token Index: 382

Text #15

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1510. Min Act: -0.0001

Data Index: 1476826 (Python Code)

Max Activating Token Index: 815

Text #16

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1825. Min Act: -0.0001

Data Index: 1599009 (Python Code)

Max Activating Token Index: 383

Text #17

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1557. Min Act: -0.0001

Data Index: 1384648 (Python Code)

Max Activating Token Index: 191

Text #18

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1663. Min Act: -0.0001

Data Index: 1611717 (Python Code)

Max Activating Token Index: 148

Text #19

Max Range: 0.1971. Min Range: -0.1971

Max Act: 0.1475. Min Act: -0.0001

Data Index: 1481424 (Python Code)

Max Activating Token Index: 412