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

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

Neuron 1804 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: 0.1628. Min Range: -0.1628

Max Act: 0.1628. Min Act: -0.0002

Data Index: 1384420 (Python Code)

Max Activating Token Index: 733

Text #1

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1577. Min Act: -0.0002

Data Index: 1509781 (Python Code)

Max Activating Token Index: 87

Text #2

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1626. Min Act: -0.0002

Data Index: 1597441 (Python Code)

Max Activating Token Index: 294

Text #3

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1587. Min Act: -0.0002

Data Index: 1482151 (Python Code)

Max Activating Token Index: 64

Text #4

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1500. Min Act: -0.0002

Data Index: 1581545 (Python Code)

Max Activating Token Index: 67

Text #5

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1512. Min Act: -0.0002

Data Index: 1572980 (Python Code)

Max Activating Token Index: 540

Text #6

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1515. Min Act: -0.0002

Data Index: 1560992 (Python Code)

Max Activating Token Index: 194

Text #7

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1472. Min Act: -0.0002

Data Index: 1476464 (Python Code)

Max Activating Token Index: 1002

Text #8

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1391. Min Act: -0.0002

Data Index: 1617126 (Python Code)

Max Activating Token Index: 229

Text #9

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1382. Min Act: -0.0002

Data Index: 1471457 (Python Code)

Max Activating Token Index: 14

Text #10

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1396. Min Act: -0.0002

Data Index: 1559182 (Python Code)

Max Activating Token Index: 31

Text #11

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1364. Min Act: -0.0002

Data Index: 1593029 (Python Code)

Max Activating Token Index: 722

Text #12

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1334. Min Act: -0.0002

Data Index: 1465850 (Python Code)

Max Activating Token Index: 57

Text #13

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1338. Min Act: -0.0002

Data Index: 1636128 (Python Code)

Max Activating Token Index: 106

Text #14

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1325. Min Act: -0.0002

Data Index: 1497822 (Python Code)

Max Activating Token Index: 75

Text #15

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1302. Min Act: -0.0002

Data Index: 1573184 (Python Code)

Max Activating Token Index: 48

Text #16

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1271. Min Act: -0.0002

Data Index: 1452792 (Python Code)

Max Activating Token Index: 711

Text #17

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1303. Min Act: -0.0002

Data Index: 1503509 (Python Code)

Max Activating Token Index: 364

Text #18

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1287. Min Act: -0.0002

Data Index: 1426742 (Python Code)

Max Activating Token Index: 526

Text #19

Max Range: 0.1628. Min Range: -0.1628

Max Act: 0.1270. Min Act: -0.0002

Data Index: 1566570 (Python Code)

Max Activating Token Index: 107