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

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

Neuron 1151 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: 5.8658. Min Range: -5.8658

Max Act: 5.8658. Min Act: -0.1700

Data Index: 108840 (C4 (Web Text))

Max Activating Token Index: 798

Text #1

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.8033. Min Act: -0.1700

Data Index: 443619 (C4 (Web Text))

Max Activating Token Index: 332

Text #2

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.7096. Min Act: -0.1700

Data Index: 89452 (C4 (Web Text))

Max Activating Token Index: 216

Text #3

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.8658. Min Act: -0.1700

Data Index: 953091 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.8033. Min Act: -0.1700

Data Index: 213035 (C4 (Web Text))

Max Activating Token Index: 829

Text #5

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.7721. Min Act: -0.1700

Data Index: 580378 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.7096. Min Act: -0.1700

Data Index: 38360 (C4 (Web Text))

Max Activating Token Index: 696

Text #7

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.7408. Min Act: -0.1700

Data Index: 755086 (C4 (Web Text))

Max Activating Token Index: 692

Text #8

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.7408. Min Act: -0.1700

Data Index: 576657 (C4 (Web Text))

Max Activating Token Index: 83

Text #9

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.7721. Min Act: -0.1700

Data Index: 751360 (C4 (Web Text))

Max Activating Token Index: 959

Text #10

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.7408. Min Act: -0.1700

Data Index: 1097946 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.7721. Min Act: -0.1700

Data Index: 935222 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.6158. Min Act: -0.1700

Data Index: 1019575 (C4 (Web Text))

Max Activating Token Index: 766

Text #13

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.7096. Min Act: -0.1700

Data Index: 1058526 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.7721. Min Act: -0.1700

Data Index: 833605 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.7408. Min Act: -0.1700

Data Index: 852297 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.7721. Min Act: -0.1700

Data Index: 428198 (C4 (Web Text))

Max Activating Token Index: 868

Text #17

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.7096. Min Act: -0.1700

Data Index: 754539 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.6783. Min Act: -0.1700

Data Index: 1053192 (C4 (Web Text))

Max Activating Token Index: 781

Text #19

Max Range: 5.8658. Min Range: -5.8658

Max Act: 5.6783. Min Act: -0.1700

Data Index: 33056 (C4 (Web Text))

Max Activating Token Index: 868