Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 831 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1742. Min Act: -0.0001

Data Index: 1457136 (Python Code)

Max Activating Token Index: 955

Text #1

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1600. Min Act: -0.0001

Data Index: 1608884 (Python Code)

Max Activating Token Index: 770

Text #2

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1635. Min Act: -0.0001

Data Index: 1479539 (Python Code)

Max Activating Token Index: 40

Text #3

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1458. Min Act: -0.0001

Data Index: 147026 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1517. Min Act: -0.0001

Data Index: 1650839 (Python Code)

Max Activating Token Index: 148

Text #5

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1470. Min Act: -0.0001

Data Index: 1474893 (Python Code)

Max Activating Token Index: 563

Text #6

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1430. Min Act: -0.0001

Data Index: 1497359 (Python Code)

Max Activating Token Index: 35

Text #7

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1537. Min Act: -0.0001

Data Index: 1499808 (Python Code)

Max Activating Token Index: 1005

Text #8

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1429. Min Act: -0.0001

Data Index: 1585939 (Python Code)

Max Activating Token Index: 50

Text #9

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1338. Min Act: -0.0001

Data Index: 1613339 (Python Code)

Max Activating Token Index: 779

Text #10

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1426. Min Act: -0.0001

Data Index: 1621595 (Python Code)

Max Activating Token Index: 300

Text #11

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1336. Min Act: -0.0001

Data Index: 1554290 (Python Code)

Max Activating Token Index: 712

Text #12

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1403. Min Act: -0.0001

Data Index: 541815 (C4 (Web Text))

Max Activating Token Index: 27

Text #13

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1318. Min Act: -0.0001

Data Index: 1462239 (Python Code)

Max Activating Token Index: 263

Text #14

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1307. Min Act: -0.0001

Data Index: 1457365 (Python Code)

Max Activating Token Index: 569

Text #15

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1337. Min Act: -0.0001

Data Index: 1588869 (Python Code)

Max Activating Token Index: 162

Text #16

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1368. Min Act: -0.0001

Data Index: 1588072 (Python Code)

Max Activating Token Index: 169

Text #17

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1279. Min Act: -0.0001

Data Index: 986478 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1314. Min Act: -0.0001

Data Index: 817375 (C4 (Web Text))

Max Activating Token Index: 423

Text #19

Max Range: 0.1742. Min Range: -0.1742

Max Act: 0.1244. Min Act: -0.0001

Data Index: 1436042 (Python Code)

Max Activating Token Index: 423