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

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

Neuron 4383 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: 0.1654. Min Range: -0.1654

Max Act: 0.1654. Min Act: -0.0002

Data Index: 1539916 (Python Code)

Max Activating Token Index: 491

Text #1

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1499. Min Act: -0.0002

Data Index: 1640192 (Python Code)

Max Activating Token Index: 143

Text #2

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1518. Min Act: -0.0002

Data Index: 1469313 (Python Code)

Max Activating Token Index: 283

Text #3

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1459. Min Act: -0.0002

Data Index: 1629925 (Python Code)

Max Activating Token Index: 563

Text #4

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1392. Min Act: -0.0002

Data Index: 1539323 (Python Code)

Max Activating Token Index: 384

Text #5

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1383. Min Act: -0.0002

Data Index: 1560099 (Python Code)

Max Activating Token Index: 430

Text #6

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1380. Min Act: -0.0002

Data Index: 1427347 (Python Code)

Max Activating Token Index: 633

Text #7

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1352. Min Act: -0.0002

Data Index: 1617609 (Python Code)

Max Activating Token Index: 894

Text #8

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1354. Min Act: -0.0002

Data Index: 1400403 (Python Code)

Max Activating Token Index: 869

Text #9

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1349. Min Act: -0.0002

Data Index: 1405230 (Python Code)

Max Activating Token Index: 387

Text #10

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1296. Min Act: -0.0002

Data Index: 1533509 (Python Code)

Max Activating Token Index: 448

Text #11

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1290. Min Act: -0.0002

Data Index: 1387592 (Python Code)

Max Activating Token Index: 557

Text #12

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1307. Min Act: -0.0002

Data Index: 1607474 (Python Code)

Max Activating Token Index: 458

Text #13

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1287. Min Act: -0.0002

Data Index: 1617330 (Python Code)

Max Activating Token Index: 482

Text #14

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1337. Min Act: -0.0002

Data Index: 1641277 (Python Code)

Max Activating Token Index: 200

Text #15

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1295. Min Act: -0.0002

Data Index: 1625755 (Python Code)

Max Activating Token Index: 415

Text #16

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1278. Min Act: -0.0002

Data Index: 1578533 (Python Code)

Max Activating Token Index: 332

Text #17

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1272. Min Act: -0.0002

Data Index: 1536874 (Python Code)

Max Activating Token Index: 700

Text #18

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1299. Min Act: -0.0002

Data Index: 1434792 (Python Code)

Max Activating Token Index: 517

Text #19

Max Range: 0.1654. Min Range: -0.1654

Max Act: 0.1297. Min Act: -0.0002

Data Index: 1373521 (Python Code)

Max Activating Token Index: 633