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

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

Neuron 4628 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.2537. Min Act: -0.0001

Data Index: 1644133 (Python Code)

Max Activating Token Index: 506

Text #1

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1774. Min Act: -0.0001

Data Index: 1578230 (Python Code)

Max Activating Token Index: 590

Text #2

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1729. Min Act: -0.0001

Data Index: 1479401 (Python Code)

Max Activating Token Index: 757

Text #3

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1676. Min Act: -0.0001

Data Index: 1570259 (Python Code)

Max Activating Token Index: 404

Text #4

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1720. Min Act: -0.0001

Data Index: 1546264 (Python Code)

Max Activating Token Index: 571

Text #5

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1648. Min Act: -0.0001

Data Index: 1653681 (Python Code)

Max Activating Token Index: 999

Text #6

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1623. Min Act: -0.0001

Data Index: 1397946 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1474. Min Act: -0.0001

Data Index: 1381868 (Python Code)

Max Activating Token Index: 1014

Text #8

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1522. Min Act: -0.0001

Data Index: 630508 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1524. Min Act: -0.0001

Data Index: 1304273 (C4 (Web Text))

Max Activating Token Index: 697

Text #10

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1472. Min Act: -0.0001

Data Index: 815756 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1478. Min Act: -0.0001

Data Index: 1026955 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1389. Min Act: -0.0001

Data Index: 1643056 (Python Code)

Max Activating Token Index: 434

Text #13

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1328. Min Act: -0.0001

Data Index: 1425085 (Python Code)

Max Activating Token Index: 993

Text #14

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1306. Min Act: -0.0001

Data Index: 1627114 (Python Code)

Max Activating Token Index: 676

Text #15

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1392. Min Act: -0.0001

Data Index: 1501375 (Python Code)

Max Activating Token Index: 993

Text #16

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1340. Min Act: -0.0001

Data Index: 992924 (C4 (Web Text))

Max Activating Token Index: 989

Text #17

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1238. Min Act: -0.0001

Data Index: 1427429 (Python Code)

Max Activating Token Index: 961

Text #18

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1367. Min Act: -0.0001

Data Index: 1482607 (Python Code)

Max Activating Token Index: 955

Text #19

Max Range: 0.2537. Min Range: -0.2537

Max Act: 0.1513. Min Act: -0.0001

Data Index: 910395 (C4 (Web Text))

Max Activating Token Index: 1023