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

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

Neuron 707 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: 3.9645. Min Range: -3.9645

Max Act: 3.9645. Min Act: -0.1700

Data Index: 134297 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 3.9645. Min Range: -3.9645

Max Act: 3.9333. Min Act: -0.1700

Data Index: 767812 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 3.9645. Min Range: -3.9645

Max Act: 3.8707. Min Act: -0.1700

Data Index: 846435 (C4 (Web Text))

Max Activating Token Index: 934

Text #3

Max Range: 3.9645. Min Range: -3.9645

Max Act: 3.5578. Min Act: -0.1700

Data Index: 1243865 (C4 (Web Text))

Max Activating Token Index: 944

Text #4

Max Range: 3.9645. Min Range: -3.9645

Max Act: 3.6204. Min Act: -0.1700

Data Index: 1148868 (C4 (Web Text))

Max Activating Token Index: 793

Text #5

Max Range: 3.9645. Min Range: -3.9645

Max Act: 3.5578. Min Act: -0.1700

Data Index: 1146372 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 3.9645. Min Range: -3.9645

Max Act: 3.5264. Min Act: -0.1700

Data Index: 637765 (C4 (Web Text))

Max Activating Token Index: 681

Text #7

Max Range: 3.9645. Min Range: -3.9645

Max Act: 3.5891. Min Act: -0.1700

Data Index: 674337 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 3.9645. Min Range: -3.9645

Max Act: 3.5264. Min Act: -0.1700

Data Index: 1117672 (C4 (Web Text))

Max Activating Token Index: 966

Text #9

Max Range: 3.9645. Min Range: -3.9645

Max Act: 3.4951. Min Act: -0.1700

Data Index: 13522 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 3.9645. Min Range: -3.9645

Max Act: 3.5264. Min Act: -0.1699

Data Index: 237099 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 3.9645. Min Range: -3.9645

Max Act: 3.5264. Min Act: -0.1699

Data Index: 1200421 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 3.9645. Min Range: -3.9645

Max Act: 3.5264. Min Act: -0.1700

Data Index: 1287125 (C4 (Web Text))

Max Activating Token Index: 796

Text #13

Max Range: 3.9645. Min Range: -3.9645

Max Act: 3.5264. Min Act: -0.1700

Data Index: 1057131 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 3.9645. Min Range: -3.9645

Max Act: 3.5264. Min Act: -0.1700

Data Index: 1348712 (C4 (Web Text))

Max Activating Token Index: 758

Text #15

Max Range: 3.9645. Min Range: -3.9645

Max Act: 3.4951. Min Act: -0.1700

Data Index: 1055922 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 3.9645. Min Range: -3.9645

Max Act: 3.5264. Min Act: -0.1700

Data Index: 1059375 (C4 (Web Text))

Max Activating Token Index: 586

Text #17

Max Range: 3.9645. Min Range: -3.9645

Max Act: 3.4951. Min Act: -0.1700

Data Index: 83635 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 3.9645. Min Range: -3.9645

Max Act: 3.4638. Min Act: -0.1700

Data Index: 627651 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 3.9645. Min Range: -3.9645

Max Act: 3.4951. Min Act: -0.1700

Data Index: 1240223 (C4 (Web Text))

Max Activating Token Index: 694