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

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

Neuron 1275 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: 3.0620. Min Range: -3.0620

Max Act: 3.0620. Min Act: -0.1695

Data Index: 1648843 (Python Code)

Max Activating Token Index: 847

Text #1

Max Range: 3.0620. Min Range: -3.0620

Max Act: 3.0376. Min Act: -0.1691

Data Index: 1365030 (Python Code)

Max Activating Token Index: 675

Text #2

Max Range: 3.0620. Min Range: -3.0620

Max Act: 3.0122. Min Act: -0.1562

Data Index: 1603634 (Python Code)

Max Activating Token Index: 971

Text #3

Max Range: 3.0620. Min Range: -3.0620

Max Act: 2.9654. Min Act: -0.1696

Data Index: 1601352 (Python Code)

Max Activating Token Index: 1023

Text #4

Max Range: 3.0620. Min Range: -3.0620

Max Act: 2.9723. Min Act: -0.1371

Data Index: 1548597 (Python Code)

Max Activating Token Index: 501

Text #5

Max Range: 3.0620. Min Range: -3.0620

Max Act: 2.9888. Min Act: -0.1698

Data Index: 1405535 (Python Code)

Max Activating Token Index: 683

Text #6

Max Range: 3.0620. Min Range: -3.0620

Max Act: 2.9576. Min Act: -0.1675

Data Index: 1443543 (Python Code)

Max Activating Token Index: 841

Text #7

Max Range: 3.0620. Min Range: -3.0620

Max Act: 2.9413. Min Act: -0.1642

Data Index: 1399210 (Python Code)

Max Activating Token Index: 527

Text #8

Max Range: 3.0620. Min Range: -3.0620

Max Act: 2.9423. Min Act: -0.1699

Data Index: 1394692 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 3.0620. Min Range: -3.0620

Max Act: 2.9446. Min Act: -0.1611

Data Index: 1374693 (Python Code)

Max Activating Token Index: 452

Text #10

Max Range: 3.0620. Min Range: -3.0620

Max Act: 2.9615. Min Act: -0.1699

Data Index: 1426842 (Python Code)

Max Activating Token Index: 973

Text #11

Max Range: 3.0620. Min Range: -3.0620

Max Act: 2.9220. Min Act: -0.1664

Data Index: 1649657 (Python Code)

Max Activating Token Index: 190

Text #12

Max Range: 3.0620. Min Range: -3.0620

Max Act: 2.9131. Min Act: -0.1699

Data Index: 1475688 (Python Code)

Max Activating Token Index: 92

Text #13

Max Range: 3.0620. Min Range: -3.0620

Max Act: 2.8617. Min Act: -0.1691

Data Index: 1502166 (Python Code)

Max Activating Token Index: 488

Text #14

Max Range: 3.0620. Min Range: -3.0620

Max Act: 2.8955. Min Act: -0.1700

Data Index: 1510409 (Python Code)

Max Activating Token Index: 161

Text #15

Max Range: 3.0620. Min Range: -3.0620

Max Act: 2.8862. Min Act: -0.1700

Data Index: 1411393 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 3.0620. Min Range: -3.0620

Max Act: 2.8442. Min Act: -0.1700

Data Index: 1470848 (Python Code)

Max Activating Token Index: 478

Text #17

Max Range: 3.0620. Min Range: -3.0620

Max Act: 2.8622. Min Act: -0.1473

Data Index: 1555016 (Python Code)

Max Activating Token Index: 370

Text #18

Max Range: 3.0620. Min Range: -3.0620

Max Act: 2.8689. Min Act: -0.1663

Data Index: 1591869 (Python Code)

Max Activating Token Index: 183

Text #19

Max Range: 3.0620. Min Range: -3.0620

Max Act: 2.8473. Min Act: -0.1688

Data Index: 1418246 (Python Code)

Max Activating Token Index: 751