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

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

Neuron 1894 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: 3.8302. Min Range: -3.8302

Max Act: 3.8302. Min Act: -0.1700

Data Index: 892770 (C4 (Web Text))

Max Activating Token Index: 554

Text #1

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.7677. Min Act: -0.1700

Data Index: 206016 (C4 (Web Text))

Max Activating Token Index: 372

Text #2

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.7520. Min Act: -0.1700

Data Index: 829901 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.7207. Min Act: -0.1700

Data Index: 448124 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.7520. Min Act: -0.1700

Data Index: 701463 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.6894. Min Act: -0.1700

Data Index: 1192784 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.6425. Min Act: -0.1700

Data Index: 936243 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.6738. Min Act: -0.1700

Data Index: 521733 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.6738. Min Act: -0.1700

Data Index: 929600 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.6738. Min Act: -0.1700

Data Index: 934395 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.6425. Min Act: -0.1700

Data Index: 192943 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.6268. Min Act: -0.1700

Data Index: 1060833 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.6268. Min Act: -0.1700

Data Index: 643694 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.6425. Min Act: -0.1700

Data Index: 1217796 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.5955. Min Act: -0.1700

Data Index: 666874 (C4 (Web Text))

Max Activating Token Index: 535

Text #15

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.6112. Min Act: -0.1700

Data Index: 937981 (C4 (Web Text))

Max Activating Token Index: 499

Text #16

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.5799. Min Act: -0.1700

Data Index: 259036 (C4 (Web Text))

Max Activating Token Index: 472

Text #17

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.6425. Min Act: -0.1700

Data Index: 1076181 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.5642. Min Act: -0.1700

Data Index: 962103 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 3.8302. Min Range: -3.8302

Max Act: 3.5799. Min Act: -0.1700

Data Index: 1045711 (C4 (Web Text))

Max Activating Token Index: 771