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

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

Neuron 643 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: 3.3579. Min Range: -3.3579

Max Act: 3.3579. Min Act: -0.1700

Data Index: 1633731 (Python Code)

Max Activating Token Index: 787

Text #1

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.3569. Min Act: -0.1696

Data Index: 1609288 (Python Code)

Max Activating Token Index: 862

Text #2

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.3300. Min Act: -0.1587

Data Index: 820318 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.2849. Min Act: -0.1695

Data Index: 1479692 (Python Code)

Max Activating Token Index: 881

Text #4

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.2694. Min Act: -0.1697

Data Index: 1532739 (Python Code)

Max Activating Token Index: 766

Text #5

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.2436. Min Act: -0.1699

Data Index: 366307 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.2382. Min Act: -0.1686

Data Index: 1023979 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.2159. Min Act: -0.1699

Data Index: 1528545 (Python Code)

Max Activating Token Index: 1012

Text #8

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.2198. Min Act: -0.1700

Data Index: 1571938 (Python Code)

Max Activating Token Index: 596

Text #9

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.2279. Min Act: -0.1697

Data Index: 1475231 (Python Code)

Max Activating Token Index: 561

Text #10

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.2087. Min Act: -0.1593

Data Index: 1461836 (Python Code)

Max Activating Token Index: 226

Text #11

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.2052. Min Act: -0.1357

Data Index: 1371033 (Python Code)

Max Activating Token Index: 671

Text #12

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.1989. Min Act: -0.1699

Data Index: 1411597 (Python Code)

Max Activating Token Index: 809

Text #13

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.2038. Min Act: -0.1700

Data Index: 1634063 (Python Code)

Max Activating Token Index: 980

Text #14

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.2026. Min Act: -0.1700

Data Index: 1426032 (Python Code)

Max Activating Token Index: 237

Text #15

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.1944. Min Act: -0.1700

Data Index: 1475000 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.2021. Min Act: -0.1566

Data Index: 1632637 (Python Code)

Max Activating Token Index: 240

Text #17

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.2116. Min Act: -0.1700

Data Index: 1385891 (Python Code)

Max Activating Token Index: 344

Text #18

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.1884. Min Act: -0.1700

Data Index: 1408239 (Python Code)

Max Activating Token Index: 97

Text #19

Max Range: 3.3579. Min Range: -3.3579

Max Act: 3.1745. Min Act: -0.1302

Data Index: 275181 (C4 (Web Text))

Max Activating Token Index: 624