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

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

Neuron 1693 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: 1.6571. Min Range: -1.6571

Max Act: 1.6571. Min Act: -0.0000

Data Index: 1569711 (Python Code)

Max Activating Token Index: 870

Text #1

Max Range: 1.6571. Min Range: -1.6571

Max Act: 1.4633. Min Act: 0.0000

Data Index: 1623315 (Python Code)

Max Activating Token Index: 372

Text #2

Max Range: 1.6571. Min Range: -1.6571

Max Act: 1.5501. Min Act: 0.0001

Data Index: 1516665 (Python Code)

Max Activating Token Index: 755

Text #3

Max Range: 1.6571. Min Range: -1.6571

Max Act: 1.5704. Min Act: -0.0000

Data Index: 1476881 (Python Code)

Max Activating Token Index: 947

Text #4

Max Range: 1.6571. Min Range: -1.6571

Max Act: 1.4783. Min Act: 0.0000

Data Index: 1417015 (Python Code)

Max Activating Token Index: 963

Text #5

Max Range: 1.6571. Min Range: -1.6571

Max Act: 1.4004. Min Act: -0.0000

Data Index: 1395516 (Python Code)

Max Activating Token Index: 495

Text #6

Max Range: 1.6571. Min Range: -1.6571

Max Act: 1.2007. Min Act: 0.0001

Data Index: 1494691 (Python Code)

Max Activating Token Index: 617

Text #7

Max Range: 1.6571. Min Range: -1.6571

Max Act: 1.2788. Min Act: 0.0000

Data Index: 1499657 (Python Code)

Max Activating Token Index: 440

Text #8

Max Range: 1.6571. Min Range: -1.6571

Max Act: 1.2606. Min Act: -0.0000

Data Index: 1598558 (Python Code)

Max Activating Token Index: 740

Text #9

Max Range: 1.6571. Min Range: -1.6571

Max Act: 1.2386. Min Act: 0.0000

Data Index: 1474804 (Python Code)

Max Activating Token Index: 439

Text #10

Max Range: 1.6571. Min Range: -1.6571

Max Act: 1.2507. Min Act: -0.0000

Data Index: 1452320 (Python Code)

Max Activating Token Index: 536

Text #11

Max Range: 1.6571. Min Range: -1.6571

Max Act: 1.2216. Min Act: 0.0000

Data Index: 1635635 (Python Code)

Max Activating Token Index: 908

Text #12

Max Range: 1.6571. Min Range: -1.6571

Max Act: 1.2277. Min Act: -0.0000

Data Index: 1623059 (Python Code)

Max Activating Token Index: 571

Text #13

Max Range: 1.6571. Min Range: -1.6571

Max Act: 1.2143. Min Act: -0.0000

Data Index: 1465012 (Python Code)

Max Activating Token Index: 1000

Text #14

Max Range: 1.6571. Min Range: -1.6571

Max Act: 1.1869. Min Act: -0.0000

Data Index: 1389536 (Python Code)

Max Activating Token Index: 941

Text #15

Max Range: 1.6571. Min Range: -1.6571

Max Act: 1.1593. Min Act: 0.0000

Data Index: 1598618 (Python Code)

Max Activating Token Index: 589

Text #16

Max Range: 1.6571. Min Range: -1.6571

Max Act: 1.0298. Min Act: -0.0000

Data Index: 1515186 (Python Code)

Max Activating Token Index: 795

Text #17

Max Range: 1.6571. Min Range: -1.6571

Max Act: 1.1480. Min Act: 0.0000

Data Index: 1599102 (Python Code)

Max Activating Token Index: 468

Text #18

Max Range: 1.6571. Min Range: -1.6571

Max Act: 1.1217. Min Act: 0.0000

Data Index: 1417115 (Python Code)

Max Activating Token Index: 646

Text #19

Max Range: 1.6571. Min Range: -1.6571

Max Act: 1.0659. Min Act: -0.0000

Data Index: 1577718 (Python Code)

Max Activating Token Index: 287