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

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

Neuron 1731 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: 3.8474. Min Range: -3.8474

Max Act: 3.8474. Min Act: -0.1700

Data Index: 1522493 (Python Code)

Max Activating Token Index: 318

Text #1

Max Range: 3.8474. Min Range: -3.8474

Max Act: 3.8407. Min Act: -0.1699

Data Index: 1553317 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 3.8474. Min Range: -3.8474

Max Act: 3.8064. Min Act: -0.1699

Data Index: 1461475 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 3.8474. Min Range: -3.8474

Max Act: 3.7433. Min Act: -0.1699

Data Index: 1588678 (Python Code)

Max Activating Token Index: 731

Text #4

Max Range: 3.8474. Min Range: -3.8474

Max Act: 3.5803. Min Act: -0.1700

Data Index: 1456716 (Python Code)

Max Activating Token Index: 1023

Text #5

Max Range: 3.8474. Min Range: -3.8474

Max Act: 3.5733. Min Act: -0.1699

Data Index: 1460129 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 3.8474. Min Range: -3.8474

Max Act: 3.5480. Min Act: -0.1700

Data Index: 1449784 (Python Code)

Max Activating Token Index: 1023

Text #7

Max Range: 3.8474. Min Range: -3.8474

Max Act: 3.5046. Min Act: -0.1700

Data Index: 1536454 (Python Code)

Max Activating Token Index: 829

Text #8

Max Range: 3.8474. Min Range: -3.8474

Max Act: 3.4739. Min Act: -0.1699

Data Index: 1515189 (Python Code)

Max Activating Token Index: 735

Text #9

Max Range: 3.8474. Min Range: -3.8474

Max Act: 3.4852. Min Act: -0.1700

Data Index: 1636393 (Python Code)

Max Activating Token Index: 746

Text #10

Max Range: 3.8474. Min Range: -3.8474

Max Act: 3.4814. Min Act: -0.1700

Data Index: 1464661 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 3.8474. Min Range: -3.8474

Max Act: 3.4671. Min Act: -0.1700

Data Index: 1654632 (Python Code)

Max Activating Token Index: 739

Text #12

Max Range: 3.8474. Min Range: -3.8474

Max Act: 3.4581. Min Act: -0.1688

Data Index: 1592739 (Python Code)

Max Activating Token Index: 751

Text #13

Max Range: 3.8474. Min Range: -3.8474

Max Act: 3.4574. Min Act: -0.1695

Data Index: 1533012 (Python Code)

Max Activating Token Index: 621

Text #14

Max Range: 3.8474. Min Range: -3.8474

Max Act: 3.4144. Min Act: -0.1700

Data Index: 1371578 (Python Code)

Max Activating Token Index: 467

Text #15

Max Range: 3.8474. Min Range: -3.8474

Max Act: 3.4192. Min Act: -0.1699

Data Index: 1639009 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 3.8474. Min Range: -3.8474

Max Act: 3.4303. Min Act: -0.1699

Data Index: 1446158 (Python Code)

Max Activating Token Index: 677

Text #17

Max Range: 3.8474. Min Range: -3.8474

Max Act: 3.4208. Min Act: -0.1661

Data Index: 1458230 (Python Code)

Max Activating Token Index: 130

Text #18

Max Range: 3.8474. Min Range: -3.8474

Max Act: 3.4324. Min Act: -0.1669

Data Index: 1377998 (Python Code)

Max Activating Token Index: 1023

Text #19

Max Range: 3.8474. Min Range: -3.8474

Max Act: 3.4298. Min Act: -0.1700

Data Index: 1442359 (Python Code)

Max Activating Token Index: 415