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

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

Neuron 1725 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3650. Min Range: -1.3650

Max Act: 1.3650. Min Act: -0.0000

Data Index: 1360858 (Python Code)

Max Activating Token Index: 475

Text #1

Max Range: 1.3650. Min Range: -1.3650

Max Act: 1.2494. Min Act: -0.0000

Data Index: 1533715 (Python Code)

Max Activating Token Index: 121

Text #2

Max Range: 1.3650. Min Range: -1.3650

Max Act: 1.2501. Min Act: -0.0000

Data Index: 1637971 (Python Code)

Max Activating Token Index: 517

Text #3

Max Range: 1.3650. Min Range: -1.3650

Max Act: 1.2550. Min Act: -0.0000

Data Index: 1596644 (Python Code)

Max Activating Token Index: 235

Text #4

Max Range: 1.3650. Min Range: -1.3650

Max Act: 1.2773. Min Act: -0.0000

Data Index: 1431385 (Python Code)

Max Activating Token Index: 140

Text #5

Max Range: 1.3650. Min Range: -1.3650

Max Act: 1.2285. Min Act: -0.0000

Data Index: 1420691 (Python Code)

Max Activating Token Index: 714

Text #6

Max Range: 1.3650. Min Range: -1.3650

Max Act: 1.2850. Min Act: -0.0000

Data Index: 1426563 (Python Code)

Max Activating Token Index: 919

Text #7

Max Range: 1.3650. Min Range: -1.3650

Max Act: 1.1475. Min Act: -0.0000

Data Index: 1641273 (Python Code)

Max Activating Token Index: 842

Text #8

Max Range: 1.3650. Min Range: -1.3650

Max Act: 1.2188. Min Act: -0.0000

Data Index: 1445495 (Python Code)

Max Activating Token Index: 26

Text #9

Max Range: 1.3650. Min Range: -1.3650

Max Act: 1.1604. Min Act: -0.0000

Data Index: 1418706 (Python Code)

Max Activating Token Index: 307

Text #10

Max Range: 1.3650. Min Range: -1.3650

Max Act: 1.1178. Min Act: -0.0000

Data Index: 1655000 (Python Code)

Max Activating Token Index: 106

Text #11

Max Range: 1.3650. Min Range: -1.3650

Max Act: 1.1040. Min Act: -0.0000

Data Index: 1476316 (Python Code)

Max Activating Token Index: 1014

Text #12

Max Range: 1.3650. Min Range: -1.3650

Max Act: 1.0445. Min Act: -0.0000

Data Index: 1528699 (Python Code)

Max Activating Token Index: 252

Text #13

Max Range: 1.3650. Min Range: -1.3650

Max Act: 0.9879. Min Act: -0.0000

Data Index: 1607173 (Python Code)

Max Activating Token Index: 73

Text #14

Max Range: 1.3650. Min Range: -1.3650

Max Act: 1.0861. Min Act: -0.0000

Data Index: 1448391 (Python Code)

Max Activating Token Index: 557

Text #15

Max Range: 1.3650. Min Range: -1.3650

Max Act: 1.0753. Min Act: -0.0000

Data Index: 1573914 (Python Code)

Max Activating Token Index: 275

Text #16

Max Range: 1.3650. Min Range: -1.3650

Max Act: 1.0144. Min Act: -0.0000

Data Index: 1647221 (Python Code)

Max Activating Token Index: 486

Text #17

Max Range: 1.3650. Min Range: -1.3650

Max Act: 1.0243. Min Act: -0.0000

Data Index: 1434122 (Python Code)

Max Activating Token Index: 104

Text #18

Max Range: 1.3650. Min Range: -1.3650

Max Act: 1.0642. Min Act: -0.0000

Data Index: 1406500 (Python Code)

Max Activating Token Index: 809

Text #19

Max Range: 1.3650. Min Range: -1.3650

Max Act: 0.9697. Min Act: -0.0000

Data Index: 1489410 (Python Code)

Max Activating Token Index: 51