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

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

Neuron 3507 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: 0.1911. Min Range: -0.1911

Max Act: 0.1845. Min Act: -0.0001

Data Index: 1454116 (Python Code)

Max Activating Token Index: 368

Text #1

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1911. Min Act: -0.0001

Data Index: 1455519 (Python Code)

Max Activating Token Index: 534

Text #2

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1786. Min Act: -0.0001

Data Index: 1453692 (Python Code)

Max Activating Token Index: 980

Text #3

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1740. Min Act: -0.0001

Data Index: 1564976 (Python Code)

Max Activating Token Index: 513

Text #4

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1707. Min Act: -0.0001

Data Index: 1576826 (Python Code)

Max Activating Token Index: 295

Text #5

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1643. Min Act: -0.0001

Data Index: 1637565 (Python Code)

Max Activating Token Index: 549

Text #6

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1516. Min Act: -0.0001

Data Index: 1653922 (Python Code)

Max Activating Token Index: 745

Text #7

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1542. Min Act: -0.0001

Data Index: 1601609 (Python Code)

Max Activating Token Index: 703

Text #8

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1504. Min Act: -0.0001

Data Index: 1455975 (Python Code)

Max Activating Token Index: 439

Text #9

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1544. Min Act: -0.0001

Data Index: 1561499 (Python Code)

Max Activating Token Index: 762

Text #10

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1432. Min Act: -0.0001

Data Index: 1612058 (Python Code)

Max Activating Token Index: 196

Text #11

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1482. Min Act: -0.0001

Data Index: 1432076 (Python Code)

Max Activating Token Index: 376

Text #12

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1462. Min Act: -0.0001

Data Index: 1441562 (Python Code)

Max Activating Token Index: 705

Text #13

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1416. Min Act: -0.0001

Data Index: 1574325 (Python Code)

Max Activating Token Index: 385

Text #14

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1424. Min Act: -0.0001

Data Index: 1560256 (Python Code)

Max Activating Token Index: 371

Text #15

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1469. Min Act: -0.0001

Data Index: 1592045 (Python Code)

Max Activating Token Index: 394

Text #16

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1439. Min Act: -0.0001

Data Index: 1401507 (Python Code)

Max Activating Token Index: 42

Text #17

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1365. Min Act: -0.0001

Data Index: 1378908 (Python Code)

Max Activating Token Index: 92

Text #18

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1407. Min Act: -0.0001

Data Index: 1418900 (Python Code)

Max Activating Token Index: 836

Text #19

Max Range: 0.1911. Min Range: -0.1911

Max Act: 0.1393. Min Act: -0.0001

Data Index: 1569160 (Python Code)

Max Activating Token Index: 617