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

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

Neuron 459 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.7433. Min Range: -5.7433

Max Act: 5.7433. Min Act: -0.1700

Data Index: 1027457 (C4 (Web Text))

Max Activating Token Index: 991

Text #1

Max Range: 5.7433. Min Range: -5.7433

Max Act: 5.6495. Min Act: -0.1700

Data Index: 828660 (C4 (Web Text))

Max Activating Token Index: 623

Text #2

Max Range: 5.7433. Min Range: -5.7433

Max Act: 5.6183. Min Act: -0.1700

Data Index: 803344 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 5.7433. Min Range: -5.7433

Max Act: 5.5245. Min Act: -0.1700

Data Index: 1320461 (C4 (Web Text))

Max Activating Token Index: 401

Text #4

Max Range: 5.7433. Min Range: -5.7433

Max Act: 5.4620. Min Act: -0.1700

Data Index: 1178499 (C4 (Web Text))

Max Activating Token Index: 916

Text #5

Max Range: 5.7433. Min Range: -5.7433

Max Act: 5.4308. Min Act: -0.1700

Data Index: 358580 (C4 (Web Text))

Max Activating Token Index: 25

Text #6

Max Range: 5.7433. Min Range: -5.7433

Max Act: 5.3683. Min Act: -0.1700

Data Index: 622363 (C4 (Web Text))

Max Activating Token Index: 647

Text #7

Max Range: 5.7433. Min Range: -5.7433

Max Act: 5.3370. Min Act: -0.1700

Data Index: 281048 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 5.7433. Min Range: -5.7433

Max Act: 5.2745. Min Act: -0.1700

Data Index: 1041095 (C4 (Web Text))

Max Activating Token Index: 974

Text #9

Max Range: 5.7433. Min Range: -5.7433

Max Act: 5.3058. Min Act: -0.1700

Data Index: 705082 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 5.7433. Min Range: -5.7433

Max Act: 5.3058. Min Act: -0.1700

Data Index: 78323 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 5.7433. Min Range: -5.7433

Max Act: 5.3683. Min Act: -0.1700

Data Index: 759682 (C4 (Web Text))

Max Activating Token Index: 963

Text #12

Max Range: 5.7433. Min Range: -5.7433

Max Act: 5.3370. Min Act: -0.1700

Data Index: 712419 (C4 (Web Text))

Max Activating Token Index: 609

Text #13

Max Range: 5.7433. Min Range: -5.7433

Max Act: 5.2745. Min Act: -0.1700

Data Index: 1352995 (C4 (Web Text))

Max Activating Token Index: 859

Text #14

Max Range: 5.7433. Min Range: -5.7433

Max Act: 5.2433. Min Act: -0.1700

Data Index: 467841 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 5.7433. Min Range: -5.7433

Max Act: 5.2433. Min Act: -0.1700

Data Index: 427923 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 5.7433. Min Range: -5.7433

Max Act: 5.2433. Min Act: -0.1700

Data Index: 1295300 (C4 (Web Text))

Max Activating Token Index: 230

Text #17

Max Range: 5.7433. Min Range: -5.7433

Max Act: 5.1808. Min Act: -0.1700

Data Index: 321468 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 5.7433. Min Range: -5.7433

Max Act: 5.2120. Min Act: -0.1700

Data Index: 854795 (C4 (Web Text))

Max Activating Token Index: 644

Text #19

Max Range: 5.7433. Min Range: -5.7433

Max Act: 5.1495. Min Act: -0.1700

Data Index: 848048 (C4 (Web Text))

Max Activating Token Index: 779