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

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

Neuron 1461 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9865. Min Range: -3.9865

Max Act: 3.9865. Min Act: -0.1700

Data Index: 672988 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 3.9865. Min Range: -3.9865

Max Act: 3.9240. Min Act: -0.1700

Data Index: 172980 (C4 (Web Text))

Max Activating Token Index: 682

Text #2

Max Range: 3.9865. Min Range: -3.9865

Max Act: 3.8302. Min Act: -0.1700

Data Index: 837357 (C4 (Web Text))

Max Activating Token Index: 643

Text #3

Max Range: 3.9865. Min Range: -3.9865

Max Act: 3.8302. Min Act: -0.1700

Data Index: 1293883 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 3.9865. Min Range: -3.9865

Max Act: 3.8615. Min Act: -0.1700

Data Index: 1187728 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 3.9865. Min Range: -3.9865

Max Act: 3.7989. Min Act: -0.1700

Data Index: 1175553 (C4 (Web Text))

Max Activating Token Index: 392

Text #6

Max Range: 3.9865. Min Range: -3.9865

Max Act: 3.7989. Min Act: -0.1700

Data Index: 1002178 (C4 (Web Text))

Max Activating Token Index: 172

Text #7

Max Range: 3.9865. Min Range: -3.9865

Max Act: 3.7989. Min Act: -0.1700

Data Index: 287171 (C4 (Web Text))

Max Activating Token Index: 602

Text #8

Max Range: 3.9865. Min Range: -3.9865

Max Act: 3.8302. Min Act: -0.1700

Data Index: 845423 (C4 (Web Text))

Max Activating Token Index: 723

Text #9

Max Range: 3.9865. Min Range: -3.9865

Max Act: 3.7989. Min Act: -0.1700

Data Index: 815960 (C4 (Web Text))

Max Activating Token Index: 982

Text #10

Max Range: 3.9865. Min Range: -3.9865

Max Act: 3.7989. Min Act: -0.1700

Data Index: 570986 (C4 (Web Text))

Max Activating Token Index: 809

Text #11

Max Range: 3.9865. Min Range: -3.9865

Max Act: 3.7676. Min Act: -0.1700

Data Index: 1094958 (C4 (Web Text))

Max Activating Token Index: 799

Text #12

Max Range: 3.9865. Min Range: -3.9865

Max Act: 3.7676. Min Act: -0.1700

Data Index: 795901 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 3.9865. Min Range: -3.9865

Max Act: 3.7989. Min Act: -0.1700

Data Index: 1343806 (C4 (Web Text))

Max Activating Token Index: 595

Text #14

Max Range: 3.9865. Min Range: -3.9865

Max Act: 3.7676. Min Act: -0.1700

Data Index: 1330225 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 3.9865. Min Range: -3.9865

Max Act: 3.7363. Min Act: -0.1700

Data Index: 676176 (C4 (Web Text))

Max Activating Token Index: 818

Text #16

Max Range: 3.9865. Min Range: -3.9865

Max Act: 3.7676. Min Act: -0.1700

Data Index: 578829 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 3.9865. Min Range: -3.9865

Max Act: 3.7363. Min Act: -0.1700

Data Index: 923533 (C4 (Web Text))

Max Activating Token Index: 293

Text #18

Max Range: 3.9865. Min Range: -3.9865

Max Act: 3.7050. Min Act: -0.1700

Data Index: 757695 (C4 (Web Text))

Max Activating Token Index: 344

Text #19

Max Range: 3.9865. Min Range: -3.9865

Max Act: 3.7363. Min Act: -0.1700

Data Index: 1132010 (C4 (Web Text))

Max Activating Token Index: 994