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

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

Neuron 2007 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: 3.2629. Min Range: -3.2629

Max Act: 3.2629. Min Act: -0.1700

Data Index: 1257604 (C4 (Web Text))

Max Activating Token Index: 239

Text #1

Max Range: 3.2629. Min Range: -3.2629

Max Act: 3.2587. Min Act: -0.1700

Data Index: 1435353 (Python Code)

Max Activating Token Index: 736

Text #2

Max Range: 3.2629. Min Range: -3.2629

Max Act: 3.2259. Min Act: -0.1700

Data Index: 652777 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 3.2629. Min Range: -3.2629

Max Act: 3.2068. Min Act: -0.1694

Data Index: 1151702 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 3.2629. Min Range: -3.2629

Max Act: 3.2090. Min Act: -0.1700

Data Index: 155021 (C4 (Web Text))

Max Activating Token Index: 212

Text #5

Max Range: 3.2629. Min Range: -3.2629

Max Act: 3.1214. Min Act: -0.1700

Data Index: 129741 (C4 (Web Text))

Max Activating Token Index: 240

Text #6

Max Range: 3.2629. Min Range: -3.2629

Max Act: 3.1189. Min Act: -0.1700

Data Index: 1424875 (Python Code)

Max Activating Token Index: 290

Text #7

Max Range: 3.2629. Min Range: -3.2629

Max Act: 3.1209. Min Act: -0.1700

Data Index: 916057 (C4 (Web Text))

Max Activating Token Index: 431

Text #8

Max Range: 3.2629. Min Range: -3.2629

Max Act: 3.1221. Min Act: -0.1652

Data Index: 137194 (C4 (Web Text))

Max Activating Token Index: 469

Text #9

Max Range: 3.2629. Min Range: -3.2629

Max Act: 3.0827. Min Act: -0.1695

Data Index: 371534 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 3.2629. Min Range: -3.2629

Max Act: 3.0860. Min Act: -0.1691

Data Index: 566662 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 3.2629. Min Range: -3.2629

Max Act: 3.0896. Min Act: -0.1699

Data Index: 1183924 (C4 (Web Text))

Max Activating Token Index: 373

Text #12

Max Range: 3.2629. Min Range: -3.2629

Max Act: 3.0743. Min Act: -0.1695

Data Index: 55881 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 3.2629. Min Range: -3.2629

Max Act: 3.0825. Min Act: -0.1699

Data Index: 198127 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 3.2629. Min Range: -3.2629

Max Act: 3.0767. Min Act: -0.1700

Data Index: 1168739 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 3.2629. Min Range: -3.2629

Max Act: 3.0669. Min Act: -0.1700

Data Index: 1180797 (C4 (Web Text))

Max Activating Token Index: 943

Text #16

Max Range: 3.2629. Min Range: -3.2629

Max Act: 3.0727. Min Act: -0.1699

Data Index: 1554591 (Python Code)

Max Activating Token Index: 146

Text #17

Max Range: 3.2629. Min Range: -3.2629

Max Act: 3.0407. Min Act: -0.1700

Data Index: 222342 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 3.2629. Min Range: -3.2629

Max Act: 3.0571. Min Act: -0.1672

Data Index: 393403 (C4 (Web Text))

Max Activating Token Index: 496

Text #19

Max Range: 3.2629. Min Range: -3.2629

Max Act: 3.0440. Min Act: -0.1687

Data Index: 682966 (C4 (Web Text))

Max Activating Token Index: 310