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

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

Neuron 144 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: 8.0828. Min Range: -8.0828

Max Act: 8.0828. Min Act: -0.1700

Data Index: 909498 (C4 (Web Text))

Max Activating Token Index: 534

Text #1

Max Range: 8.0828. Min Range: -8.0828

Max Act: 7.8953. Min Act: -0.1700

Data Index: 229339 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 8.0828. Min Range: -8.0828

Max Act: 7.8328. Min Act: -0.1700

Data Index: 7349 (C4 (Web Text))

Max Activating Token Index: 627

Text #3

Max Range: 8.0828. Min Range: -8.0828

Max Act: 7.8328. Min Act: -0.1700

Data Index: 73731 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 8.0828. Min Range: -8.0828

Max Act: 7.7703. Min Act: -0.1700

Data Index: 300978 (C4 (Web Text))

Max Activating Token Index: 804

Text #5

Max Range: 8.0828. Min Range: -8.0828

Max Act: 7.6453. Min Act: -0.1700

Data Index: 1057780 (C4 (Web Text))

Max Activating Token Index: 653

Text #6

Max Range: 8.0828. Min Range: -8.0828

Max Act: 7.7078. Min Act: -0.1700

Data Index: 638154 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 8.0828. Min Range: -8.0828

Max Act: 7.6453. Min Act: -0.1700

Data Index: 188787 (C4 (Web Text))

Max Activating Token Index: 340

Text #8

Max Range: 8.0828. Min Range: -8.0828

Max Act: 7.5828. Min Act: -0.1700

Data Index: 303642 (C4 (Web Text))

Max Activating Token Index: 497

Text #9

Max Range: 8.0828. Min Range: -8.0828

Max Act: 7.5828. Min Act: -0.1700

Data Index: 1041245 (C4 (Web Text))

Max Activating Token Index: 408

Text #10

Max Range: 8.0828. Min Range: -8.0828

Max Act: 7.6453. Min Act: -0.1700

Data Index: 651571 (C4 (Web Text))

Max Activating Token Index: 966

Text #11

Max Range: 8.0828. Min Range: -8.0828

Max Act: 7.5203. Min Act: -0.1700

Data Index: 477685 (C4 (Web Text))

Max Activating Token Index: 428

Text #12

Max Range: 8.0828. Min Range: -8.0828

Max Act: 7.4578. Min Act: -0.1700

Data Index: 646421 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 8.0828. Min Range: -8.0828

Max Act: 7.4578. Min Act: -0.1700

Data Index: 914944 (C4 (Web Text))

Max Activating Token Index: 143

Text #14

Max Range: 8.0828. Min Range: -8.0828

Max Act: 7.4578. Min Act: -0.1700

Data Index: 796441 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 8.0828. Min Range: -8.0828

Max Act: 7.3953. Min Act: -0.1700

Data Index: 1175299 (C4 (Web Text))

Max Activating Token Index: 400

Text #16

Max Range: 8.0828. Min Range: -8.0828

Max Act: 7.5203. Min Act: -0.1700

Data Index: 1211070 (C4 (Web Text))

Max Activating Token Index: 266

Text #17

Max Range: 8.0828. Min Range: -8.0828

Max Act: 7.3328. Min Act: -0.1700

Data Index: 991449 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 8.0828. Min Range: -8.0828

Max Act: 7.3953. Min Act: -0.1700

Data Index: 793538 (C4 (Web Text))

Max Activating Token Index: 238

Text #19

Max Range: 8.0828. Min Range: -8.0828

Max Act: 7.4578. Min Act: -0.1699

Data Index: 17167 (C4 (Web Text))

Max Activating Token Index: 393