Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2020 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.6719. Min Range: -3.6719

Max Act: 3.6719. Min Act: -0.1700

Data Index: 890377 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 3.6719. Min Range: -3.6719

Max Act: 3.5780. Min Act: -0.1700

Data Index: 481124 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 3.6719. Min Range: -3.6719

Max Act: 3.5467. Min Act: -0.1700

Data Index: 1321449 (C4 (Web Text))

Max Activating Token Index: 223

Text #3

Max Range: 3.6719. Min Range: -3.6719

Max Act: 3.4840. Min Act: -0.1700

Data Index: 1096797 (C4 (Web Text))

Max Activating Token Index: 567

Text #4

Max Range: 3.6719. Min Range: -3.6719

Max Act: 3.4840. Min Act: -0.1700

Data Index: 565917 (C4 (Web Text))

Max Activating Token Index: 543

Text #5

Max Range: 3.6719. Min Range: -3.6719

Max Act: 3.4840. Min Act: -0.1700

Data Index: 493516 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 3.6719. Min Range: -3.6719

Max Act: 3.4840. Min Act: -0.1700

Data Index: 810300 (C4 (Web Text))

Max Activating Token Index: 995

Text #7

Max Range: 3.6719. Min Range: -3.6719

Max Act: 3.4840. Min Act: -0.1694

Data Index: 110228 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.6719. Min Range: -3.6719

Max Act: 3.4213. Min Act: -0.1700

Data Index: 82480 (C4 (Web Text))

Max Activating Token Index: 899

Text #9

Max Range: 3.6719. Min Range: -3.6719

Max Act: 3.4527. Min Act: -0.1700

Data Index: 581546 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 3.6719. Min Range: -3.6719

Max Act: 3.4213. Min Act: -0.1700

Data Index: 504824 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 3.6719. Min Range: -3.6719

Max Act: 3.4213. Min Act: -0.1700

Data Index: 311922 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 3.6719. Min Range: -3.6719

Max Act: 3.3899. Min Act: -0.1700

Data Index: 46149 (C4 (Web Text))

Max Activating Token Index: 874

Text #13

Max Range: 3.6719. Min Range: -3.6719

Max Act: 3.3899. Min Act: -0.1700

Data Index: 860194 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 3.6719. Min Range: -3.6719

Max Act: 3.3586. Min Act: -0.1700

Data Index: 495365 (C4 (Web Text))

Max Activating Token Index: 235

Text #15

Max Range: 3.6719. Min Range: -3.6719

Max Act: 3.3899. Min Act: -0.1700

Data Index: 392334 (C4 (Web Text))

Max Activating Token Index: 627

Text #16

Max Range: 3.6719. Min Range: -3.6719

Max Act: 3.3899. Min Act: -0.1700

Data Index: 606482 (C4 (Web Text))

Max Activating Token Index: 725

Text #17

Max Range: 3.6719. Min Range: -3.6719

Max Act: 3.3586. Min Act: -0.1700

Data Index: 1056565 (C4 (Web Text))

Max Activating Token Index: 430

Text #18

Max Range: 3.6719. Min Range: -3.6719

Max Act: 3.3899. Min Act: -0.1700

Data Index: 251931 (C4 (Web Text))

Max Activating Token Index: 821

Text #19

Max Range: 3.6719. Min Range: -3.6719

Max Act: 3.3586. Min Act: -0.1700

Data Index: 1082963 (C4 (Web Text))

Max Activating Token Index: 939