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

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

Neuron 605 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: 5.4701. Min Range: -5.4701

Max Act: 5.4701. Min Act: -0.1700

Data Index: 951706 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 5.4701. Min Range: -5.4701

Max Act: 5.3451. Min Act: -0.1700

Data Index: 473589 (C4 (Web Text))

Max Activating Token Index: 203

Text #2

Max Range: 5.4701. Min Range: -5.4701

Max Act: 5.2826. Min Act: -0.1700

Data Index: 299285 (C4 (Web Text))

Max Activating Token Index: 156

Text #3

Max Range: 5.4701. Min Range: -5.4701

Max Act: 5.3763. Min Act: -0.1700

Data Index: 1287015 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 5.4701. Min Range: -5.4701

Max Act: 5.2826. Min Act: -0.1700

Data Index: 634477 (C4 (Web Text))

Max Activating Token Index: 563

Text #5

Max Range: 5.4701. Min Range: -5.4701

Max Act: 5.3138. Min Act: -0.1700

Data Index: 854942 (C4 (Web Text))

Max Activating Token Index: 926

Text #6

Max Range: 5.4701. Min Range: -5.4701

Max Act: 5.2201. Min Act: -0.1700

Data Index: 868627 (C4 (Web Text))

Max Activating Token Index: 1016

Text #7

Max Range: 5.4701. Min Range: -5.4701

Max Act: 5.2201. Min Act: -0.1700

Data Index: 578201 (C4 (Web Text))

Max Activating Token Index: 142

Text #8

Max Range: 5.4701. Min Range: -5.4701

Max Act: 5.2513. Min Act: -0.1700

Data Index: 443863 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 5.4701. Min Range: -5.4701

Max Act: 5.2201. Min Act: -0.1700

Data Index: 719335 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 5.4701. Min Range: -5.4701

Max Act: 5.1576. Min Act: -0.1700

Data Index: 556996 (C4 (Web Text))

Max Activating Token Index: 956

Text #11

Max Range: 5.4701. Min Range: -5.4701

Max Act: 5.1576. Min Act: -0.1700

Data Index: 655005 (C4 (Web Text))

Max Activating Token Index: 1008

Text #12

Max Range: 5.4701. Min Range: -5.4701

Max Act: 5.2513. Min Act: -0.1700

Data Index: 605455 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 5.4701. Min Range: -5.4701

Max Act: 5.1576. Min Act: -0.1700

Data Index: 580649 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 5.4701. Min Range: -5.4701

Max Act: 5.2201. Min Act: -0.1700

Data Index: 215317 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 5.4701. Min Range: -5.4701

Max Act: 5.1576. Min Act: -0.1700

Data Index: 476386 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 5.4701. Min Range: -5.4701

Max Act: 5.1888. Min Act: -0.1700

Data Index: 465212 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 5.4701. Min Range: -5.4701

Max Act: 5.1888. Min Act: -0.1700

Data Index: 534934 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 5.4701. Min Range: -5.4701

Max Act: 5.0638. Min Act: -0.1700

Data Index: 433411 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 5.4701. Min Range: -5.4701

Max Act: 5.0951. Min Act: -0.1700

Data Index: 267708 (C4 (Web Text))

Max Activating Token Index: 225