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

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

Neuron 856 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1023. Min Range: -3.1023

Max Act: 3.0707. Min Act: -0.1700

Data Index: 335162 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 3.1023. Min Range: -3.1023

Max Act: 3.1023. Min Act: -0.1700

Data Index: 904396 (C4 (Web Text))

Max Activating Token Index: 490

Text #2

Max Range: 3.1023. Min Range: -3.1023

Max Act: 3.0550. Min Act: -0.1700

Data Index: 627567 (C4 (Web Text))

Max Activating Token Index: 522

Text #3

Max Range: 3.1023. Min Range: -3.1023

Max Act: 2.9759. Min Act: -0.1700

Data Index: 1058497 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 3.1023. Min Range: -3.1023

Max Act: 3.0392. Min Act: -0.1700

Data Index: 769469 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 3.1023. Min Range: -3.1023

Max Act: 3.0234. Min Act: -0.1700

Data Index: 558354 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 3.1023. Min Range: -3.1023

Max Act: 3.0076. Min Act: -0.1700

Data Index: 268808 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 3.1023. Min Range: -3.1023

Max Act: 3.0392. Min Act: -0.1700

Data Index: 95744 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 3.1023. Min Range: -3.1023

Max Act: 3.0076. Min Act: -0.1700

Data Index: 272506 (C4 (Web Text))

Max Activating Token Index: 581

Text #9

Max Range: 3.1023. Min Range: -3.1023

Max Act: 3.0392. Min Act: -0.1700

Data Index: 231760 (C4 (Web Text))

Max Activating Token Index: 511

Text #10

Max Range: 3.1023. Min Range: -3.1023

Max Act: 3.0392. Min Act: -0.1700

Data Index: 780433 (C4 (Web Text))

Max Activating Token Index: 98

Text #11

Max Range: 3.1023. Min Range: -3.1023

Max Act: 3.0076. Min Act: -0.1700

Data Index: 555230 (C4 (Web Text))

Max Activating Token Index: 998

Text #12

Max Range: 3.1023. Min Range: -3.1023

Max Act: 3.0234. Min Act: -0.1700

Data Index: 1023801 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 3.1023. Min Range: -3.1023

Max Act: 2.9759. Min Act: -0.1700

Data Index: 869298 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 3.1023. Min Range: -3.1023

Max Act: 2.9759. Min Act: -0.1700

Data Index: 1348731 (C4 (Web Text))

Max Activating Token Index: 671

Text #15

Max Range: 3.1023. Min Range: -3.1023

Max Act: 2.9759. Min Act: -0.1700

Data Index: 578783 (C4 (Web Text))

Max Activating Token Index: 597

Text #16

Max Range: 3.1023. Min Range: -3.1023

Max Act: 2.9759. Min Act: -0.1700

Data Index: 1248321 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 3.1023. Min Range: -3.1023

Max Act: 3.0076. Min Act: -0.1700

Data Index: 657120 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 3.1023. Min Range: -3.1023

Max Act: 2.9601. Min Act: -0.1700

Data Index: 18700 (C4 (Web Text))

Max Activating Token Index: 949

Text #19

Max Range: 3.1023. Min Range: -3.1023

Max Act: 2.9918. Min Act: -0.1700

Data Index: 128484 (C4 (Web Text))

Max Activating Token Index: 1005