Model: GELU Model: 1 Layers, 2048 Neurons per Layer

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

Neuron 20 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 3.4045. Min Range: -3.4045

Max Act: 3.4045. Min Act: -0.1699

Data Index: 1370843 (Python Code)

Max Activating Token Index: 701

Text #1

Max Range: 3.4045. Min Range: -3.4045

Max Act: 3.2536. Min Act: -0.1700

Data Index: 1604960 (Python Code)

Max Activating Token Index: 714

Text #2

Max Range: 3.4045. Min Range: -3.4045

Max Act: 3.2298. Min Act: -0.1654

Data Index: 1621772 (Python Code)

Max Activating Token Index: 906

Text #3

Max Range: 3.4045. Min Range: -3.4045

Max Act: 3.2246. Min Act: -0.1698

Data Index: 1635792 (Python Code)

Max Activating Token Index: 420

Text #4

Max Range: 3.4045. Min Range: -3.4045

Max Act: 3.2420. Min Act: -0.1700

Data Index: 1387647 (Python Code)

Max Activating Token Index: 501

Text #5

Max Range: 3.4045. Min Range: -3.4045

Max Act: 3.1918. Min Act: -0.1700

Data Index: 1586842 (Python Code)

Max Activating Token Index: 660

Text #6

Max Range: 3.4045. Min Range: -3.4045

Max Act: 3.2009. Min Act: -0.1700

Data Index: 1449077 (Python Code)

Max Activating Token Index: 896

Text #7

Max Range: 3.4045. Min Range: -3.4045

Max Act: 3.1696. Min Act: -0.1577

Data Index: 1394579 (Python Code)

Max Activating Token Index: 266

Text #8

Max Range: 3.4045. Min Range: -3.4045

Max Act: 3.1737. Min Act: -0.1700

Data Index: 1389539 (Python Code)

Max Activating Token Index: 141

Text #9

Max Range: 3.4045. Min Range: -3.4045

Max Act: 3.1743. Min Act: -0.1699

Data Index: 1549048 (Python Code)

Max Activating Token Index: 843

Text #10

Max Range: 3.4045. Min Range: -3.4045

Max Act: 3.1669. Min Act: -0.1643

Data Index: 1404347 (Python Code)

Max Activating Token Index: 316

Text #11

Max Range: 3.4045. Min Range: -3.4045

Max Act: 3.1507. Min Act: -0.1700

Data Index: 194136 (C4 (Web Text))

Max Activating Token Index: 999

Text #12

Max Range: 3.4045. Min Range: -3.4045

Max Act: 3.1421. Min Act: -0.1698

Data Index: 1615883 (Python Code)

Max Activating Token Index: 682

Text #13

Max Range: 3.4045. Min Range: -3.4045

Max Act: 3.1551. Min Act: -0.1700

Data Index: 1378793 (Python Code)

Max Activating Token Index: 368

Text #14

Max Range: 3.4045. Min Range: -3.4045

Max Act: 3.1324. Min Act: -0.1700

Data Index: 1409665 (Python Code)

Max Activating Token Index: 591

Text #15

Max Range: 3.4045. Min Range: -3.4045

Max Act: 3.1354. Min Act: -0.1699

Data Index: 1556907 (Python Code)

Max Activating Token Index: 455

Text #16

Max Range: 3.4045. Min Range: -3.4045

Max Act: 3.1512. Min Act: -0.1700

Data Index: 1552927 (Python Code)

Max Activating Token Index: 757

Text #17

Max Range: 3.4045. Min Range: -3.4045

Max Act: 3.1554. Min Act: -0.1698

Data Index: 1337257 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 3.4045. Min Range: -3.4045

Max Act: 3.1184. Min Act: -0.1682

Data Index: 1523274 (Python Code)

Max Activating Token Index: 67

Text #19

Max Range: 3.4045. Min Range: -3.4045

Max Act: 3.1252. Min Act: -0.1654

Data Index: 1642459 (Python Code)

Max Activating Token Index: 132