Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1300 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.2130. Min Range: -3.2130

Max Act: 3.1815. Min Act: -0.1700

Data Index: 1230627 (C4 (Web Text))

Max Activating Token Index: 101

Text #1

Max Range: 3.2130. Min Range: -3.2130

Max Act: 3.2130. Min Act: -0.1700

Data Index: 461099 (C4 (Web Text))

Max Activating Token Index: 737

Text #2

Max Range: 3.2130. Min Range: -3.2130

Max Act: 3.1815. Min Act: -0.1700

Data Index: 1044696 (C4 (Web Text))

Max Activating Token Index: 288

Text #3

Max Range: 3.2130. Min Range: -3.2130

Max Act: 3.2130. Min Act: -0.1700

Data Index: 1034272 (C4 (Web Text))

Max Activating Token Index: 275

Text #4

Max Range: 3.2130. Min Range: -3.2130

Max Act: 3.0870. Min Act: -0.1700

Data Index: 1318681 (C4 (Web Text))

Max Activating Token Index: 103

Text #5

Max Range: 3.2130. Min Range: -3.2130

Max Act: 3.1185. Min Act: -0.1700

Data Index: 397858 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 3.2130. Min Range: -3.2130

Max Act: 3.0870. Min Act: -0.1700

Data Index: 798311 (C4 (Web Text))

Max Activating Token Index: 782

Text #7

Max Range: 3.2130. Min Range: -3.2130

Max Act: 3.0554. Min Act: -0.1700

Data Index: 907829 (C4 (Web Text))

Max Activating Token Index: 230

Text #8

Max Range: 3.2130. Min Range: -3.2130

Max Act: 3.0238. Min Act: -0.1700

Data Index: 57569 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 3.2130. Min Range: -3.2130

Max Act: 2.9922. Min Act: -0.1700

Data Index: 852751 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 3.2130. Min Range: -3.2130

Max Act: 2.9922. Min Act: -0.1700

Data Index: 731374 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 3.2130. Min Range: -3.2130

Max Act: 2.9922. Min Act: -0.1700

Data Index: 652992 (C4 (Web Text))

Max Activating Token Index: 108

Text #12

Max Range: 3.2130. Min Range: -3.2130

Max Act: 2.9606. Min Act: -0.1700

Data Index: 986163 (C4 (Web Text))

Max Activating Token Index: 553

Text #13

Max Range: 3.2130. Min Range: -3.2130

Max Act: 2.9606. Min Act: -0.1700

Data Index: 1295039 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 3.2130. Min Range: -3.2130

Max Act: 2.9922. Min Act: -0.1700

Data Index: 567342 (C4 (Web Text))

Max Activating Token Index: 699

Text #15

Max Range: 3.2130. Min Range: -3.2130

Max Act: 3.0238. Min Act: -0.1700

Data Index: 409616 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 3.2130. Min Range: -3.2130

Max Act: 2.9922. Min Act: -0.1700

Data Index: 786792 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 3.2130. Min Range: -3.2130

Max Act: 2.9289. Min Act: -0.1700

Data Index: 1141456 (C4 (Web Text))

Max Activating Token Index: 815

Text #18

Max Range: 3.2130. Min Range: -3.2130

Max Act: 2.9606. Min Act: -0.1700

Data Index: 1431 (C4 (Web Text))

Max Activating Token Index: 815

Text #19

Max Range: 3.2130. Min Range: -3.2130

Max Act: 3.0238. Min Act: -0.1700

Data Index: 867276 (C4 (Web Text))

Max Activating Token Index: 478