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

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

Neuron 2415 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1565. Min Act: -0.0002

Data Index: 1592012 (Python Code)

Max Activating Token Index: 158

Text #1

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1550. Min Act: -0.0002

Data Index: 1448395 (Python Code)

Max Activating Token Index: 154

Text #2

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1546. Min Act: -0.0002

Data Index: 1599778 (Python Code)

Max Activating Token Index: 56

Text #3

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1563. Min Act: -0.0002

Data Index: 1615194 (Python Code)

Max Activating Token Index: 956

Text #4

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1536. Min Act: -0.0002

Data Index: 1509304 (Python Code)

Max Activating Token Index: 156

Text #5

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1520. Min Act: -0.0002

Data Index: 1387497 (Python Code)

Max Activating Token Index: 261

Text #6

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1483. Min Act: -0.0002

Data Index: 1436860 (Python Code)

Max Activating Token Index: 64

Text #7

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1493. Min Act: -0.0002

Data Index: 1611388 (Python Code)

Max Activating Token Index: 353

Text #8

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1437. Min Act: -0.0002

Data Index: 1637688 (Python Code)

Max Activating Token Index: 479

Text #9

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1472. Min Act: -0.0002

Data Index: 1491024 (Python Code)

Max Activating Token Index: 75

Text #10

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1430. Min Act: -0.0002

Data Index: 1542091 (Python Code)

Max Activating Token Index: 777

Text #11

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1429. Min Act: -0.0002

Data Index: 1463392 (Python Code)

Max Activating Token Index: 102

Text #12

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1429. Min Act: -0.0002

Data Index: 1568805 (Python Code)

Max Activating Token Index: 169

Text #13

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1399. Min Act: -0.0002

Data Index: 1526289 (Python Code)

Max Activating Token Index: 917

Text #14

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1402. Min Act: -0.0002

Data Index: 1537687 (Python Code)

Max Activating Token Index: 718

Text #15

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1393. Min Act: -0.0002

Data Index: 1418522 (Python Code)

Max Activating Token Index: 273

Text #16

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1367. Min Act: -0.0002

Data Index: 1416862 (Python Code)

Max Activating Token Index: 709

Text #17

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1403. Min Act: -0.0002

Data Index: 1436323 (Python Code)

Max Activating Token Index: 652

Text #18

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1402. Min Act: -0.0002

Data Index: 1603638 (Python Code)

Max Activating Token Index: 274

Text #19

Max Range: 0.1565. Min Range: -0.1565

Max Act: 0.1401. Min Act: -0.0002

Data Index: 1640682 (Python Code)

Max Activating Token Index: 767