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

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

Neuron 1496 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.5486. Min Range: -5.5486

Max Act: 5.5486. Min Act: -0.1700

Data Index: 136665 (C4 (Web Text))

Max Activating Token Index: 976

Text #1

Max Range: 5.5486. Min Range: -5.5486

Max Act: 5.3611. Min Act: -0.1700

Data Index: 1306761 (C4 (Web Text))

Max Activating Token Index: 1004

Text #2

Max Range: 5.5486. Min Range: -5.5486

Max Act: 5.1736. Min Act: -0.1700

Data Index: 420465 (C4 (Web Text))

Max Activating Token Index: 13

Text #3

Max Range: 5.5486. Min Range: -5.5486

Max Act: 5.1423. Min Act: -0.1700

Data Index: 149287 (C4 (Web Text))

Max Activating Token Index: 541

Text #4

Max Range: 5.5486. Min Range: -5.5486

Max Act: 5.1736. Min Act: -0.1700

Data Index: 1182996 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 5.5486. Min Range: -5.5486

Max Act: 5.1423. Min Act: -0.1700

Data Index: 17189 (C4 (Web Text))

Max Activating Token Index: 938

Text #6

Max Range: 5.5486. Min Range: -5.5486

Max Act: 5.1736. Min Act: -0.1700

Data Index: 1351920 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 5.5486. Min Range: -5.5486

Max Act: 5.1423. Min Act: -0.1700

Data Index: 33257 (C4 (Web Text))

Max Activating Token Index: 675

Text #8

Max Range: 5.5486. Min Range: -5.5486

Max Act: 5.1111. Min Act: -0.1700

Data Index: 227005 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 5.5486. Min Range: -5.5486

Max Act: 5.1423. Min Act: -0.1700

Data Index: 1279825 (C4 (Web Text))

Max Activating Token Index: 14

Text #10

Max Range: 5.5486. Min Range: -5.5486

Max Act: 5.0798. Min Act: -0.1700

Data Index: 1272010 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 5.5486. Min Range: -5.5486

Max Act: 5.0798. Min Act: -0.1700

Data Index: 220779 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 5.5486. Min Range: -5.5486

Max Act: 5.1111. Min Act: -0.1700

Data Index: 891887 (C4 (Web Text))

Max Activating Token Index: 58

Text #13

Max Range: 5.5486. Min Range: -5.5486

Max Act: 5.1111. Min Act: -0.1700

Data Index: 1338895 (C4 (Web Text))

Max Activating Token Index: 417

Text #14

Max Range: 5.5486. Min Range: -5.5486

Max Act: 5.0486. Min Act: -0.1700

Data Index: 1225747 (C4 (Web Text))

Max Activating Token Index: 410

Text #15

Max Range: 5.5486. Min Range: -5.5486

Max Act: 5.0486. Min Act: -0.1700

Data Index: 1194454 (C4 (Web Text))

Max Activating Token Index: 221

Text #16

Max Range: 5.5486. Min Range: -5.5486

Max Act: 5.0486. Min Act: -0.1700

Data Index: 981794 (C4 (Web Text))

Max Activating Token Index: 707

Text #17

Max Range: 5.5486. Min Range: -5.5486

Max Act: 5.0798. Min Act: -0.1700

Data Index: 282831 (C4 (Web Text))

Max Activating Token Index: 674

Text #18

Max Range: 5.5486. Min Range: -5.5486

Max Act: 5.0798. Min Act: -0.1700

Data Index: 1123905 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 5.5486. Min Range: -5.5486

Max Act: 4.9861. Min Act: -0.1700

Data Index: 823254 (C4 (Web Text))

Max Activating Token Index: 849