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

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

Neuron 1012 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: 4.8550. Min Range: -4.8550

Max Act: 4.8550. Min Act: -0.1700

Data Index: 1411148 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 4.8550. Min Range: -4.8550

Max Act: 4.6392. Min Act: -0.1700

Data Index: 1391077 (Python Code)

Max Activating Token Index: 771

Text #2

Max Range: 4.8550. Min Range: -4.8550

Max Act: 4.6597. Min Act: -0.1700

Data Index: 1557610 (Python Code)

Max Activating Token Index: 213

Text #3

Max Range: 4.8550. Min Range: -4.8550

Max Act: 4.6245. Min Act: -0.1700

Data Index: 1369531 (Python Code)

Max Activating Token Index: 554

Text #4

Max Range: 4.8550. Min Range: -4.8550

Max Act: 4.5964. Min Act: -0.1700

Data Index: 1586405 (Python Code)

Max Activating Token Index: 471

Text #5

Max Range: 4.8550. Min Range: -4.8550

Max Act: 4.5753. Min Act: -0.1700

Data Index: 1540621 (Python Code)

Max Activating Token Index: 464

Text #6

Max Range: 4.8550. Min Range: -4.8550

Max Act: 4.5590. Min Act: -0.1700

Data Index: 1452409 (Python Code)

Max Activating Token Index: 414

Text #7

Max Range: 4.8550. Min Range: -4.8550

Max Act: 4.5751. Min Act: -0.1699

Data Index: 1608129 (Python Code)

Max Activating Token Index: 769

Text #8

Max Range: 4.8550. Min Range: -4.8550

Max Act: 4.5618. Min Act: -0.1700

Data Index: 1514873 (Python Code)

Max Activating Token Index: 397

Text #9

Max Range: 4.8550. Min Range: -4.8550

Max Act: 4.5736. Min Act: -0.1700

Data Index: 1578223 (Python Code)

Max Activating Token Index: 605

Text #10

Max Range: 4.8550. Min Range: -4.8550

Max Act: 4.5786. Min Act: -0.1700

Data Index: 1479336 (Python Code)

Max Activating Token Index: 173

Text #11

Max Range: 4.8550. Min Range: -4.8550

Max Act: 4.5097. Min Act: -0.1699

Data Index: 1387522 (Python Code)

Max Activating Token Index: 576

Text #12

Max Range: 4.8550. Min Range: -4.8550

Max Act: 4.5308. Min Act: -0.1699

Data Index: 1480819 (Python Code)

Max Activating Token Index: 125

Text #13

Max Range: 4.8550. Min Range: -4.8550

Max Act: 4.4882. Min Act: -0.1700

Data Index: 1406099 (Python Code)

Max Activating Token Index: 848

Text #14

Max Range: 4.8550. Min Range: -4.8550

Max Act: 4.5127. Min Act: -0.1699

Data Index: 1385367 (Python Code)

Max Activating Token Index: 189

Text #15

Max Range: 4.8550. Min Range: -4.8550

Max Act: 4.4876. Min Act: -0.1699

Data Index: 1415660 (Python Code)

Max Activating Token Index: 870

Text #16

Max Range: 4.8550. Min Range: -4.8550

Max Act: 4.4850. Min Act: -0.1700

Data Index: 1530582 (Python Code)

Max Activating Token Index: 521

Text #17

Max Range: 4.8550. Min Range: -4.8550

Max Act: 4.4882. Min Act: -0.1696

Data Index: 1397782 (Python Code)

Max Activating Token Index: 110

Text #18

Max Range: 4.8550. Min Range: -4.8550

Max Act: 4.4233. Min Act: -0.1700

Data Index: 1506952 (Python Code)

Max Activating Token Index: 886

Text #19

Max Range: 4.8550. Min Range: -4.8550

Max Act: 4.4518. Min Act: -0.1699

Data Index: 1577466 (Python Code)

Max Activating Token Index: 628