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

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

Neuron 698 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1789. Min Act: -0.0001

Data Index: 867397 (C4 (Web Text))

Max Activating Token Index: 540

Text #1

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1701. Min Act: -0.0001

Data Index: 1426742 (Python Code)

Max Activating Token Index: 37

Text #2

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1722. Min Act: -0.0001

Data Index: 1123193 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1716. Min Act: -0.0001

Data Index: 778596 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1577. Min Act: -0.0001

Data Index: 785308 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1647. Min Act: -0.0001

Data Index: 863596 (C4 (Web Text))

Max Activating Token Index: 178

Text #6

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1584. Min Act: -0.0001

Data Index: 689966 (C4 (Web Text))

Max Activating Token Index: 1007

Text #7

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1507. Min Act: -0.0001

Data Index: 1365925 (Python Code)

Max Activating Token Index: 614

Text #8

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1533. Min Act: -0.0001

Data Index: 228604 (C4 (Web Text))

Max Activating Token Index: 887

Text #9

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1542. Min Act: -0.0001

Data Index: 1407540 (Python Code)

Max Activating Token Index: 907

Text #10

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1520. Min Act: -0.0001

Data Index: 815814 (C4 (Web Text))

Max Activating Token Index: 423

Text #11

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1401. Min Act: -0.0001

Data Index: 791657 (C4 (Web Text))

Max Activating Token Index: 484

Text #12

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1514. Min Act: -0.0001

Data Index: 857139 (C4 (Web Text))

Max Activating Token Index: 190

Text #13

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1376. Min Act: -0.0001

Data Index: 1337973 (C4 (Web Text))

Max Activating Token Index: 990

Text #14

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1413. Min Act: -0.0001

Data Index: 1272531 (C4 (Web Text))

Max Activating Token Index: 955

Text #15

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1393. Min Act: -0.0001

Data Index: 94804 (C4 (Web Text))

Max Activating Token Index: 469

Text #16

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1401. Min Act: -0.0001

Data Index: 1299935 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1452. Min Act: -0.0001

Data Index: 1317216 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1267. Min Act: -0.0001

Data Index: 420287 (C4 (Web Text))

Max Activating Token Index: 746

Text #19

Max Range: 0.1789. Min Range: -0.1789

Max Act: 0.1324. Min Act: -0.0001

Data Index: 473744 (C4 (Web Text))

Max Activating Token Index: 212