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

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

Neuron 1394 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: 5.5433. Min Range: -5.5433

Max Act: 5.5433. Min Act: -0.1700

Data Index: 1122632 (C4 (Web Text))

Max Activating Token Index: 595

Text #1

Max Range: 5.5433. Min Range: -5.5433

Max Act: 5.4886. Min Act: -0.1700

Data Index: 96507 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 5.5433. Min Range: -5.5433

Max Act: 5.5198. Min Act: -0.1700

Data Index: 1303829 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 5.5433. Min Range: -5.5433

Max Act: 5.3948. Min Act: -0.1700

Data Index: 598440 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 5.5433. Min Range: -5.5433

Max Act: 5.3558. Min Act: -0.1700

Data Index: 206376 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 5.5433. Min Range: -5.5433

Max Act: 5.2776. Min Act: -0.1700

Data Index: 94055 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 5.5433. Min Range: -5.5433

Max Act: 5.2464. Min Act: -0.1700

Data Index: 1137004 (C4 (Web Text))

Max Activating Token Index: 208

Text #7

Max Range: 5.5433. Min Range: -5.5433

Max Act: 5.2386. Min Act: -0.1700

Data Index: 1332992 (C4 (Web Text))

Max Activating Token Index: 559

Text #8

Max Range: 5.5433. Min Range: -5.5433

Max Act: 5.1683. Min Act: -0.1700

Data Index: 1340139 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 5.5433. Min Range: -5.5433

Max Act: 5.2229. Min Act: -0.1700

Data Index: 1305341 (C4 (Web Text))

Max Activating Token Index: 640

Text #10

Max Range: 5.5433. Min Range: -5.5433

Max Act: 5.1683. Min Act: -0.1700

Data Index: 783087 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 5.5433. Min Range: -5.5433

Max Act: 5.1526. Min Act: -0.1700

Data Index: 174457 (C4 (Web Text))

Max Activating Token Index: 582

Text #12

Max Range: 5.5433. Min Range: -5.5433

Max Act: 5.0198. Min Act: -0.1700

Data Index: 1290446 (C4 (Web Text))

Max Activating Token Index: 176

Text #13

Max Range: 5.5433. Min Range: -5.5433

Max Act: 5.0745. Min Act: -0.1700

Data Index: 992626 (C4 (Web Text))

Max Activating Token Index: 279

Text #14

Max Range: 5.5433. Min Range: -5.5433

Max Act: 5.1057. Min Act: -0.1700

Data Index: 1162180 (C4 (Web Text))

Max Activating Token Index: 439

Text #15

Max Range: 5.5433. Min Range: -5.5433

Max Act: 5.0354. Min Act: -0.1700

Data Index: 1220715 (C4 (Web Text))

Max Activating Token Index: 827

Text #16

Max Range: 5.5433. Min Range: -5.5433

Max Act: 5.0823. Min Act: -0.1700

Data Index: 280478 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 5.5433. Min Range: -5.5433

Max Act: 5.0432. Min Act: -0.1700

Data Index: 96264 (C4 (Web Text))

Max Activating Token Index: 457

Text #18

Max Range: 5.5433. Min Range: -5.5433

Max Act: 5.0198. Min Act: -0.1700

Data Index: 570950 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 5.5433. Min Range: -5.5433

Max Act: 4.9651. Min Act: -0.1700

Data Index: 942033 (C4 (Web Text))

Max Activating Token Index: 667