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

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

Neuron 6032 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: 0.1623. Min Range: -0.1623

Max Act: 0.1623. Min Act: -0.0002

Data Index: 1468036 (Python Code)

Max Activating Token Index: 115

Text #1

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1530. Min Act: -0.0002

Data Index: 412828 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1497. Min Act: -0.0002

Data Index: 1428715 (Python Code)

Max Activating Token Index: 72

Text #3

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1499. Min Act: -0.0002

Data Index: 1438142 (Python Code)

Max Activating Token Index: 185

Text #4

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1489. Min Act: -0.0002

Data Index: 1465832 (Python Code)

Max Activating Token Index: 532

Text #5

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1503. Min Act: -0.0002

Data Index: 1374339 (Python Code)

Max Activating Token Index: 289

Text #6

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1472. Min Act: -0.0002

Data Index: 1493867 (Python Code)

Max Activating Token Index: 813

Text #7

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1452. Min Act: -0.0002

Data Index: 1650763 (Python Code)

Max Activating Token Index: 753

Text #8

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1415. Min Act: -0.0002

Data Index: 1617986 (Python Code)

Max Activating Token Index: 6

Text #9

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1436. Min Act: -0.0002

Data Index: 1596343 (Python Code)

Max Activating Token Index: 189

Text #10

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1405. Min Act: -0.0002

Data Index: 1526047 (Python Code)

Max Activating Token Index: 33

Text #11

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1387. Min Act: -0.0002

Data Index: 1372715 (Python Code)

Max Activating Token Index: 398

Text #12

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1411. Min Act: -0.0002

Data Index: 1373023 (Python Code)

Max Activating Token Index: 153

Text #13

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1379. Min Act: -0.0002

Data Index: 1529661 (Python Code)

Max Activating Token Index: 900

Text #14

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1411. Min Act: -0.0002

Data Index: 1365756 (Python Code)

Max Activating Token Index: 384

Text #15

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1368. Min Act: -0.0002

Data Index: 1577508 (Python Code)

Max Activating Token Index: 316

Text #16

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1394. Min Act: -0.0002

Data Index: 1496806 (Python Code)

Max Activating Token Index: 102

Text #17

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1347. Min Act: -0.0002

Data Index: 1494193 (Python Code)

Max Activating Token Index: 886

Text #18

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1377. Min Act: -0.0002

Data Index: 1552529 (Python Code)

Max Activating Token Index: 312

Text #19

Max Range: 0.1623. Min Range: -0.1623

Max Act: 0.1354. Min Act: -0.0002

Data Index: 1483837 (Python Code)

Max Activating Token Index: 315