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

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

Neuron 1187 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1698. Min Act: -0.0000

Data Index: 570402 (C4 (Web Text))

Max Activating Token Index: 685

Text #1

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1638. Min Act: -0.0000

Data Index: 1526776 (Python Code)

Max Activating Token Index: 615

Text #2

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1695. Min Act: -0.0000

Data Index: 1471412 (Python Code)

Max Activating Token Index: 858

Text #3

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1635. Min Act: -0.0000

Data Index: 91011 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1405. Min Act: -0.0000

Data Index: 1433897 (Python Code)

Max Activating Token Index: 809

Text #5

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1545. Min Act: -0.0000

Data Index: 1624178 (Python Code)

Max Activating Token Index: 535

Text #6

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1539. Min Act: -0.0000

Data Index: 1451794 (Python Code)

Max Activating Token Index: 596

Text #7

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1533. Min Act: -0.0000

Data Index: 1210969 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1581. Min Act: -0.0000

Data Index: 1540563 (Python Code)

Max Activating Token Index: 602

Text #9

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1532. Min Act: -0.0000

Data Index: 154373 (C4 (Web Text))

Max Activating Token Index: 626

Text #10

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1520. Min Act: -0.0000

Data Index: 1433028 (Python Code)

Max Activating Token Index: 371

Text #11

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1511. Min Act: -0.0000

Data Index: 379559 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1485. Min Act: -0.0000

Data Index: 1306551 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1463. Min Act: -0.0000

Data Index: 1625385 (Python Code)

Max Activating Token Index: 282

Text #14

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1417. Min Act: -0.0000

Data Index: 947751 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1554. Min Act: -0.0000

Data Index: 1482700 (Python Code)

Max Activating Token Index: 980

Text #16

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1444. Min Act: -0.0000

Data Index: 503751 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1393. Min Act: -0.0000

Data Index: 779836 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1316. Min Act: -0.0000

Data Index: 1478598 (Python Code)

Max Activating Token Index: 441

Text #19

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1325. Min Act: -0.0000

Data Index: 1370125 (Python Code)

Max Activating Token Index: 844