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

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

Neuron 24 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: 2.9752. Min Range: -2.9752

Max Act: 2.9752. Min Act: -0.1700

Data Index: 1500051 (Python Code)

Max Activating Token Index: 145

Text #1

Max Range: 2.9752. Min Range: -2.9752

Max Act: 2.9169. Min Act: -0.0985

Data Index: 1405326 (Python Code)

Max Activating Token Index: 826

Text #2

Max Range: 2.9752. Min Range: -2.9752

Max Act: 2.8817. Min Act: -0.1695

Data Index: 1438864 (Python Code)

Max Activating Token Index: 897

Text #3

Max Range: 2.9752. Min Range: -2.9752

Max Act: 2.8552. Min Act: -0.1633

Data Index: 1589466 (Python Code)

Max Activating Token Index: 241

Text #4

Max Range: 2.9752. Min Range: -2.9752

Max Act: 2.8677. Min Act: -0.1266

Data Index: 1646234 (Python Code)

Max Activating Token Index: 291

Text #5

Max Range: 2.9752. Min Range: -2.9752

Max Act: 2.8264. Min Act: -0.1550

Data Index: 1500128 (Python Code)

Max Activating Token Index: 703

Text #6

Max Range: 2.9752. Min Range: -2.9752

Max Act: 2.8418. Min Act: -0.1600

Data Index: 1585772 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 2.9752. Min Range: -2.9752

Max Act: 2.8038. Min Act: -0.1190

Data Index: 1459473 (Python Code)

Max Activating Token Index: 308

Text #8

Max Range: 2.9752. Min Range: -2.9752

Max Act: 2.8114. Min Act: -0.1623

Data Index: 1556290 (Python Code)

Max Activating Token Index: 317

Text #9

Max Range: 2.9752. Min Range: -2.9752

Max Act: 2.8022. Min Act: -0.1692

Data Index: 1428143 (Python Code)

Max Activating Token Index: 268

Text #10

Max Range: 2.9752. Min Range: -2.9752

Max Act: 2.7906. Min Act: -0.1699

Data Index: 1379402 (Python Code)

Max Activating Token Index: 589

Text #11

Max Range: 2.9752. Min Range: -2.9752

Max Act: 2.7579. Min Act: -0.1511

Data Index: 1508887 (Python Code)

Max Activating Token Index: 435

Text #12

Max Range: 2.9752. Min Range: -2.9752

Max Act: 2.7858. Min Act: -0.1242

Data Index: 1417533 (Python Code)

Max Activating Token Index: 346

Text #13

Max Range: 2.9752. Min Range: -2.9752

Max Act: 2.7640. Min Act: -0.1421

Data Index: 1368304 (Python Code)

Max Activating Token Index: 117

Text #14

Max Range: 2.9752. Min Range: -2.9752

Max Act: 2.7589. Min Act: -0.1699

Data Index: 1426176 (Python Code)

Max Activating Token Index: 1013

Text #15

Max Range: 2.9752. Min Range: -2.9752

Max Act: 2.7548. Min Act: -0.1700

Data Index: 1395895 (Python Code)

Max Activating Token Index: 336

Text #16

Max Range: 2.9752. Min Range: -2.9752

Max Act: 2.7376. Min Act: -0.1150

Data Index: 1442739 (Python Code)

Max Activating Token Index: 783

Text #17

Max Range: 2.9752. Min Range: -2.9752

Max Act: 2.7448. Min Act: -0.0832

Data Index: 1369254 (Python Code)

Max Activating Token Index: 195

Text #18

Max Range: 2.9752. Min Range: -2.9752

Max Act: 2.7418. Min Act: -0.1598

Data Index: 1576785 (Python Code)

Max Activating Token Index: 733

Text #19

Max Range: 2.9752. Min Range: -2.9752

Max Act: 2.7154. Min Act: -0.1354

Data Index: 1476771 (Python Code)

Max Activating Token Index: 357