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

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

Neuron 1261 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.8449. Min Range: -5.8449

Max Act: 5.8449. Min Act: -0.1700

Data Index: 1218524 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 5.8449. Min Range: -5.8449

Max Act: 5.7511. Min Act: -0.1700

Data Index: 102460 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 5.8449. Min Range: -5.8449

Max Act: 5.7511. Min Act: -0.1700

Data Index: 1103626 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 5.8449. Min Range: -5.8449

Max Act: 5.7199. Min Act: -0.1700

Data Index: 713590 (C4 (Web Text))

Max Activating Token Index: 894

Text #4

Max Range: 5.8449. Min Range: -5.8449

Max Act: 5.6574. Min Act: -0.1700

Data Index: 354155 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 5.8449. Min Range: -5.8449

Max Act: 5.5949. Min Act: -0.1700

Data Index: 238977 (C4 (Web Text))

Max Activating Token Index: 407

Text #6

Max Range: 5.8449. Min Range: -5.8449

Max Act: 5.5949. Min Act: -0.1700

Data Index: 820048 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 5.8449. Min Range: -5.8449

Max Act: 5.5324. Min Act: -0.1700

Data Index: 216989 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 5.8449. Min Range: -5.8449

Max Act: 5.5324. Min Act: -0.1699

Data Index: 239612 (C4 (Web Text))

Max Activating Token Index: 973

Text #9

Max Range: 5.8449. Min Range: -5.8449

Max Act: 5.5324. Min Act: -0.1700

Data Index: 613971 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 5.8449. Min Range: -5.8449

Max Act: 5.5324. Min Act: -0.1698

Data Index: 396691 (C4 (Web Text))

Max Activating Token Index: 432

Text #11

Max Range: 5.8449. Min Range: -5.8449

Max Act: 5.5011. Min Act: -0.1699

Data Index: 595973 (C4 (Web Text))

Max Activating Token Index: 573

Text #12

Max Range: 5.8449. Min Range: -5.8449

Max Act: 5.4699. Min Act: -0.1700

Data Index: 78183 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 5.8449. Min Range: -5.8449

Max Act: 5.4699. Min Act: -0.1700

Data Index: 1217032 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 5.8449. Min Range: -5.8449

Max Act: 5.4386. Min Act: -0.1700

Data Index: 1029779 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 5.8449. Min Range: -5.8449

Max Act: 5.4386. Min Act: -0.1700

Data Index: 182980 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 5.8449. Min Range: -5.8449

Max Act: 5.4386. Min Act: -0.1700

Data Index: 389916 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 5.8449. Min Range: -5.8449

Max Act: 5.4386. Min Act: -0.1700

Data Index: 1047491 (C4 (Web Text))

Max Activating Token Index: 589

Text #18

Max Range: 5.8449. Min Range: -5.8449

Max Act: 5.4386. Min Act: -0.1700

Data Index: 109972 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 5.8449. Min Range: -5.8449

Max Act: 5.4386. Min Act: -0.1700

Data Index: 760544 (C4 (Web Text))

Max Activating Token Index: 165