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

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

Neuron 3072 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1646. Min Act: -0.0001

Data Index: 406099 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1555. Min Act: -0.0001

Data Index: 1472778 (Python Code)

Max Activating Token Index: 396

Text #2

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1551. Min Act: -0.0001

Data Index: 1371003 (Python Code)

Max Activating Token Index: 840

Text #3

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1472. Min Act: -0.0001

Data Index: 1496512 (Python Code)

Max Activating Token Index: 372

Text #4

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1594. Min Act: -0.0001

Data Index: 1368501 (Python Code)

Max Activating Token Index: 230

Text #5

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1476. Min Act: -0.0001

Data Index: 1111517 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1468. Min Act: -0.0001

Data Index: 1654004 (Python Code)

Max Activating Token Index: 704

Text #7

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1446. Min Act: -0.0001

Data Index: 1633343 (Python Code)

Max Activating Token Index: 945

Text #8

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1442. Min Act: -0.0001

Data Index: 1483534 (Python Code)

Max Activating Token Index: 390

Text #9

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1336. Min Act: -0.0001

Data Index: 1588566 (Python Code)

Max Activating Token Index: 367

Text #10

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1405. Min Act: -0.0001

Data Index: 1616577 (Python Code)

Max Activating Token Index: 792

Text #11

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1327. Min Act: -0.0001

Data Index: 1480487 (Python Code)

Max Activating Token Index: 808

Text #12

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1379. Min Act: -0.0001

Data Index: 1439127 (Python Code)

Max Activating Token Index: 660

Text #13

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1406. Min Act: -0.0001

Data Index: 1485016 (Python Code)

Max Activating Token Index: 698

Text #14

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1323. Min Act: -0.0001

Data Index: 1553388 (Python Code)

Max Activating Token Index: 254

Text #15

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1390. Min Act: -0.0001

Data Index: 1602177 (Python Code)

Max Activating Token Index: 181

Text #16

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1452. Min Act: -0.0001

Data Index: 1326376 (C4 (Web Text))

Max Activating Token Index: 3

Text #17

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1448. Min Act: -0.0001

Data Index: 1556592 (Python Code)

Max Activating Token Index: 654

Text #18

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1462. Min Act: -0.0001

Data Index: 1505893 (Python Code)

Max Activating Token Index: 187

Text #19

Max Range: 0.1646. Min Range: -0.1646

Max Act: 0.1447. Min Act: -0.0001

Data Index: 497195 (C4 (Web Text))

Max Activating Token Index: 249