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

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

Neuron 5206 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1802. Min Act: -0.0001

Data Index: 1563037 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1600. Min Act: -0.0001

Data Index: 1615245 (Python Code)

Max Activating Token Index: 47

Text #2

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1628. Min Act: -0.0001

Data Index: 1653985 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1642. Min Act: -0.0001

Data Index: 1636805 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1558. Min Act: -0.0001

Data Index: 1639545 (Python Code)

Max Activating Token Index: 32

Text #5

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1570. Min Act: -0.0001

Data Index: 1598825 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1544. Min Act: -0.0001

Data Index: 1435201 (Python Code)

Max Activating Token Index: 52

Text #7

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1528. Min Act: -0.0001

Data Index: 1488797 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1465. Min Act: -0.0001

Data Index: 1380092 (Python Code)

Max Activating Token Index: 51

Text #9

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1463. Min Act: -0.0001

Data Index: 1624096 (Python Code)

Max Activating Token Index: 37

Text #10

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1426. Min Act: -0.0001

Data Index: 1422249 (Python Code)

Max Activating Token Index: 65

Text #11

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1440. Min Act: -0.0001

Data Index: 1419227 (Python Code)

Max Activating Token Index: 125

Text #12

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1442. Min Act: -0.0001

Data Index: 1541734 (Python Code)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1420. Min Act: -0.0001

Data Index: 1494316 (Python Code)

Max Activating Token Index: 19

Text #14

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1413. Min Act: -0.0001

Data Index: 1498587 (Python Code)

Max Activating Token Index: 943

Text #15

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1386. Min Act: -0.0001

Data Index: 1561669 (Python Code)

Max Activating Token Index: 16

Text #16

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1383. Min Act: -0.0001

Data Index: 1494932 (Python Code)

Max Activating Token Index: 101

Text #17

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1371. Min Act: -0.0001

Data Index: 1604565 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1345. Min Act: -0.0001

Data Index: 1572360 (Python Code)

Max Activating Token Index: 13

Text #19

Max Range: 0.1802. Min Range: -0.1802

Max Act: 0.1324. Min Act: -0.0002

Data Index: 1440011 (Python Code)

Max Activating Token Index: 5