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

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

Neuron 337 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: 3.8310. Min Range: -3.8310

Max Act: 3.7684. Min Act: -0.1700

Data Index: 378767 (C4 (Web Text))

Max Activating Token Index: 465

Text #1

Max Range: 3.8310. Min Range: -3.8310

Max Act: 3.8310. Min Act: -0.1700

Data Index: 134837 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 3.8310. Min Range: -3.8310

Max Act: 3.7058. Min Act: -0.1700

Data Index: 1051664 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 3.8310. Min Range: -3.8310

Max Act: 3.7371. Min Act: -0.1700

Data Index: 615788 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 3.8310. Min Range: -3.8310

Max Act: 3.7058. Min Act: -0.1700

Data Index: 1312872 (C4 (Web Text))

Max Activating Token Index: 52

Text #5

Max Range: 3.8310. Min Range: -3.8310

Max Act: 3.6745. Min Act: -0.1700

Data Index: 1248438 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 3.8310. Min Range: -3.8310

Max Act: 3.7058. Min Act: -0.1700

Data Index: 1041109 (C4 (Web Text))

Max Activating Token Index: 261

Text #7

Max Range: 3.8310. Min Range: -3.8310

Max Act: 3.6745. Min Act: -0.1700

Data Index: 1313218 (C4 (Web Text))

Max Activating Token Index: 564

Text #8

Max Range: 3.8310. Min Range: -3.8310

Max Act: 3.6432. Min Act: -0.1700

Data Index: 1285206 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 3.8310. Min Range: -3.8310

Max Act: 3.7058. Min Act: -0.1700

Data Index: 1266657 (C4 (Web Text))

Max Activating Token Index: 878

Text #10

Max Range: 3.8310. Min Range: -3.8310

Max Act: 3.6745. Min Act: -0.1700

Data Index: 1202491 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 3.8310. Min Range: -3.8310

Max Act: 3.6432. Min Act: -0.1700

Data Index: 142078 (C4 (Web Text))

Max Activating Token Index: 163

Text #12

Max Range: 3.8310. Min Range: -3.8310

Max Act: 3.6119. Min Act: -0.1700

Data Index: 1038398 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 3.8310. Min Range: -3.8310

Max Act: 3.7058. Min Act: -0.1700

Data Index: 347808 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 3.8310. Min Range: -3.8310

Max Act: 3.6119. Min Act: -0.1700

Data Index: 960556 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 3.8310. Min Range: -3.8310

Max Act: 3.5806. Min Act: -0.1700

Data Index: 1169656 (C4 (Web Text))

Max Activating Token Index: 412

Text #16

Max Range: 3.8310. Min Range: -3.8310

Max Act: 3.6432. Min Act: -0.1700

Data Index: 742873 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 3.8310. Min Range: -3.8310

Max Act: 3.6119. Min Act: -0.1700

Data Index: 1043131 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 3.8310. Min Range: -3.8310

Max Act: 3.6119. Min Act: -0.1700

Data Index: 1231513 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 3.8310. Min Range: -3.8310

Max Act: 3.5806. Min Act: -0.1700

Data Index: 1070675 (C4 (Web Text))

Max Activating Token Index: 103