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

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

Neuron 1899 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: 5.7984. Min Range: -5.7984

Max Act: 5.7984. Min Act: -0.1700

Data Index: 1056729 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 5.7984. Min Range: -5.7984

Max Act: 5.7359. Min Act: -0.1700

Data Index: 667593 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 5.7984. Min Range: -5.7984

Max Act: 5.7359. Min Act: -0.1700

Data Index: 273135 (C4 (Web Text))

Max Activating Token Index: 1004

Text #3

Max Range: 5.7984. Min Range: -5.7984

Max Act: 5.7359. Min Act: -0.1700

Data Index: 14158 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 5.7984. Min Range: -5.7984

Max Act: 5.7359. Min Act: -0.1700

Data Index: 943746 (C4 (Web Text))

Max Activating Token Index: 740

Text #5

Max Range: 5.7984. Min Range: -5.7984

Max Act: 5.7359. Min Act: -0.1700

Data Index: 292657 (C4 (Web Text))

Max Activating Token Index: 906

Text #6

Max Range: 5.7984. Min Range: -5.7984

Max Act: 5.6422. Min Act: -0.1700

Data Index: 469975 (C4 (Web Text))

Max Activating Token Index: 502

Text #7

Max Range: 5.7984. Min Range: -5.7984

Max Act: 5.6109. Min Act: -0.1700

Data Index: 1087100 (C4 (Web Text))

Max Activating Token Index: 943

Text #8

Max Range: 5.7984. Min Range: -5.7984

Max Act: 5.6422. Min Act: -0.1700

Data Index: 1165278 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 5.7984. Min Range: -5.7984

Max Act: 5.5484. Min Act: -0.1700

Data Index: 112483 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 5.7984. Min Range: -5.7984

Max Act: 5.5484. Min Act: -0.1700

Data Index: 1157814 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 5.7984. Min Range: -5.7984

Max Act: 5.4859. Min Act: -0.1700

Data Index: 535506 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 5.7984. Min Range: -5.7984

Max Act: 5.4547. Min Act: -0.1700

Data Index: 454664 (C4 (Web Text))

Max Activating Token Index: 1019

Text #13

Max Range: 5.7984. Min Range: -5.7984

Max Act: 5.5484. Min Act: -0.1700

Data Index: 558066 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 5.7984. Min Range: -5.7984

Max Act: 5.4859. Min Act: -0.1700

Data Index: 553385 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 5.7984. Min Range: -5.7984

Max Act: 5.4547. Min Act: -0.1700

Data Index: 653125 (C4 (Web Text))

Max Activating Token Index: 442

Text #16

Max Range: 5.7984. Min Range: -5.7984

Max Act: 5.4859. Min Act: -0.1700

Data Index: 476545 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 5.7984. Min Range: -5.7984

Max Act: 5.5172. Min Act: -0.1700

Data Index: 787175 (C4 (Web Text))

Max Activating Token Index: 443

Text #18

Max Range: 5.7984. Min Range: -5.7984

Max Act: 5.4547. Min Act: -0.1700

Data Index: 716057 (C4 (Web Text))

Max Activating Token Index: 679

Text #19

Max Range: 5.7984. Min Range: -5.7984

Max Act: 5.4234. Min Act: -0.1700

Data Index: 702373 (C4 (Web Text))

Max Activating Token Index: 122