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

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

Neuron 9 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.2648. Min Range: -5.2648

Max Act: 5.2648. Min Act: -0.1700

Data Index: 474221 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 5.2648. Min Range: -5.2648

Max Act: 5.1710. Min Act: -0.1700

Data Index: 1032908 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 5.2648. Min Range: -5.2648

Max Act: 5.2335. Min Act: -0.1700

Data Index: 963705 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 5.2648. Min Range: -5.2648

Max Act: 5.2335. Min Act: -0.1700

Data Index: 1251505 (C4 (Web Text))

Max Activating Token Index: 812

Text #4

Max Range: 5.2648. Min Range: -5.2648

Max Act: 5.2335. Min Act: -0.1700

Data Index: 373401 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 5.2648. Min Range: -5.2648

Max Act: 5.2335. Min Act: -0.1700

Data Index: 1158612 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 5.2648. Min Range: -5.2648

Max Act: 5.1710. Min Act: -0.1700

Data Index: 1014144 (C4 (Web Text))

Max Activating Token Index: 945

Text #7

Max Range: 5.2648. Min Range: -5.2648

Max Act: 5.1398. Min Act: -0.1700

Data Index: 988199 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 5.2648. Min Range: -5.2648

Max Act: 5.1710. Min Act: -0.1700

Data Index: 487377 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 5.2648. Min Range: -5.2648

Max Act: 5.1710. Min Act: -0.1700

Data Index: 1332469 (C4 (Web Text))

Max Activating Token Index: 322

Text #10

Max Range: 5.2648. Min Range: -5.2648

Max Act: 5.1710. Min Act: -0.1700

Data Index: 702085 (C4 (Web Text))

Max Activating Token Index: 785

Text #11

Max Range: 5.2648. Min Range: -5.2648

Max Act: 5.1398. Min Act: -0.1700

Data Index: 834504 (C4 (Web Text))

Max Activating Token Index: 582

Text #12

Max Range: 5.2648. Min Range: -5.2648

Max Act: 5.1398. Min Act: -0.1700

Data Index: 1327517 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 5.2648. Min Range: -5.2648

Max Act: 5.0773. Min Act: -0.1700

Data Index: 802040 (C4 (Web Text))

Max Activating Token Index: 577

Text #14

Max Range: 5.2648. Min Range: -5.2648

Max Act: 5.1710. Min Act: -0.1700

Data Index: 224920 (C4 (Web Text))

Max Activating Token Index: 414

Text #15

Max Range: 5.2648. Min Range: -5.2648

Max Act: 5.0773. Min Act: -0.1700

Data Index: 980486 (C4 (Web Text))

Max Activating Token Index: 114

Text #16

Max Range: 5.2648. Min Range: -5.2648

Max Act: 5.1398. Min Act: -0.1700

Data Index: 587926 (C4 (Web Text))

Max Activating Token Index: 200

Text #17

Max Range: 5.2648. Min Range: -5.2648

Max Act: 5.1085. Min Act: -0.1700

Data Index: 378754 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 5.2648. Min Range: -5.2648

Max Act: 5.1085. Min Act: -0.1700

Data Index: 128624 (C4 (Web Text))

Max Activating Token Index: 191

Text #19

Max Range: 5.2648. Min Range: -5.2648

Max Act: 5.1710. Min Act: -0.1700

Data Index: 1121841 (C4 (Web Text))

Max Activating Token Index: 378