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

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

Neuron 698 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0496. Min Range: -1.0496

Max Act: 1.0496. Min Act: -0.0000

Data Index: 1534787 (Python Code)

Max Activating Token Index: 889

Text #1

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.9783. Min Act: 0.0001

Data Index: 1362916 (Python Code)

Max Activating Token Index: 645

Text #2

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.9723. Min Act: 0.0000

Data Index: 1547386 (Python Code)

Max Activating Token Index: 409

Text #3

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.9511. Min Act: -0.0000

Data Index: 1472580 (Python Code)

Max Activating Token Index: 317

Text #4

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.9439. Min Act: -0.0000

Data Index: 1565224 (Python Code)

Max Activating Token Index: 83

Text #5

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.9463. Min Act: 0.0000

Data Index: 1399749 (Python Code)

Max Activating Token Index: 665

Text #6

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.9343. Min Act: -0.0000

Data Index: 1570010 (Python Code)

Max Activating Token Index: 321

Text #7

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.9149. Min Act: -0.0000

Data Index: 1628566 (Python Code)

Max Activating Token Index: 211

Text #8

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.9281. Min Act: 0.0000

Data Index: 1468156 (Python Code)

Max Activating Token Index: 640

Text #9

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.9773. Min Act: 0.0000

Data Index: 1518988 (Python Code)

Max Activating Token Index: 622

Text #10

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.9222. Min Act: -0.0000

Data Index: 1362562 (Python Code)

Max Activating Token Index: 294

Text #11

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.9188. Min Act: -0.0000

Data Index: 1381311 (Python Code)

Max Activating Token Index: 892

Text #12

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.9304. Min Act: -0.0000

Data Index: 1393061 (Python Code)

Max Activating Token Index: 237

Text #13

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.8851. Min Act: -0.0000

Data Index: 1463802 (Python Code)

Max Activating Token Index: 980

Text #14

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.8873. Min Act: -0.0000

Data Index: 1556441 (Python Code)

Max Activating Token Index: 839

Text #15

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.9080. Min Act: -0.0000

Data Index: 1406688 (Python Code)

Max Activating Token Index: 205

Text #16

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.9181. Min Act: 0.0000

Data Index: 1607296 (Python Code)

Max Activating Token Index: 270

Text #17

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.8653. Min Act: -0.0000

Data Index: 1489375 (Python Code)

Max Activating Token Index: 562

Text #18

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.8415. Min Act: -0.0000

Data Index: 1596019 (Python Code)

Max Activating Token Index: 901

Text #19

Max Range: 1.0496. Min Range: -1.0496

Max Act: 0.8583. Min Act: -0.0000

Data Index: 1629474 (Python Code)

Max Activating Token Index: 391