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

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

Neuron 1324 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.2115. Min Act: -0.0001

Data Index: 1519312 (Python Code)

Max Activating Token Index: 19

Text #1

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1782. Min Act: -0.0001

Data Index: 1589499 (Python Code)

Max Activating Token Index: 549

Text #2

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1823. Min Act: -0.0001

Data Index: 1631024 (Python Code)

Max Activating Token Index: 601

Text #3

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1657. Min Act: -0.0001

Data Index: 1414404 (Python Code)

Max Activating Token Index: 698

Text #4

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1602. Min Act: -0.0001

Data Index: 1392030 (Python Code)

Max Activating Token Index: 561

Text #5

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1631. Min Act: -0.0001

Data Index: 1557975 (Python Code)

Max Activating Token Index: 38

Text #6

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1559. Min Act: -0.0001

Data Index: 1368261 (Python Code)

Max Activating Token Index: 118

Text #7

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1533. Min Act: -0.0001

Data Index: 1614133 (Python Code)

Max Activating Token Index: 504

Text #8

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1681. Min Act: -0.0001

Data Index: 1591838 (Python Code)

Max Activating Token Index: 115

Text #9

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1629. Min Act: -0.0001

Data Index: 1473973 (Python Code)

Max Activating Token Index: 311

Text #10

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1674. Min Act: -0.0001

Data Index: 1446884 (Python Code)

Max Activating Token Index: 132

Text #11

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1505. Min Act: -0.0001

Data Index: 1569920 (Python Code)

Max Activating Token Index: 134

Text #12

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1491. Min Act: -0.0001

Data Index: 1590161 (Python Code)

Max Activating Token Index: 257

Text #13

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1552. Min Act: -0.0001

Data Index: 1505698 (Python Code)

Max Activating Token Index: 540

Text #14

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1479. Min Act: -0.0001

Data Index: 1573883 (Python Code)

Max Activating Token Index: 452

Text #15

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1428. Min Act: -0.0001

Data Index: 1543362 (Python Code)

Max Activating Token Index: 189

Text #16

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1441. Min Act: -0.0001

Data Index: 1422955 (Python Code)

Max Activating Token Index: 212

Text #17

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1380. Min Act: -0.0001

Data Index: 1544613 (Python Code)

Max Activating Token Index: 720

Text #18

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1426. Min Act: -0.0001

Data Index: 1563706 (Python Code)

Max Activating Token Index: 461

Text #19

Max Range: 0.2115. Min Range: -0.2115

Max Act: 0.1420. Min Act: -0.0001

Data Index: 1513682 (Python Code)

Max Activating Token Index: 385