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

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

Neuron 1564 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: 5.8047. Min Range: -5.8047

Max Act: 5.8047. Min Act: -0.1700

Data Index: 1129298 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.6641. Min Act: -0.1700

Data Index: 912220 (C4 (Web Text))

Max Activating Token Index: 96

Text #2

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.5391. Min Act: -0.1700

Data Index: 898308 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.5547. Min Act: -0.1700

Data Index: 10176 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.4922. Min Act: -0.1700

Data Index: 925183 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.4453. Min Act: -0.1700

Data Index: 1106412 (C4 (Web Text))

Max Activating Token Index: 601

Text #6

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.4141. Min Act: -0.1700

Data Index: 64928 (C4 (Web Text))

Max Activating Token Index: 468

Text #7

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.4141. Min Act: -0.1700

Data Index: 629555 (C4 (Web Text))

Max Activating Token Index: 1012

Text #8

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.4609. Min Act: -0.1700

Data Index: 481150 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.3672. Min Act: -0.1700

Data Index: 1273610 (C4 (Web Text))

Max Activating Token Index: 309

Text #10

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.3828. Min Act: -0.1700

Data Index: 658375 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.3672. Min Act: -0.1700

Data Index: 740150 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.4141. Min Act: -0.1700

Data Index: 190180 (C4 (Web Text))

Max Activating Token Index: 870

Text #13

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.3203. Min Act: -0.1700

Data Index: 662247 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.2891. Min Act: -0.1700

Data Index: 1255715 (C4 (Web Text))

Max Activating Token Index: 10

Text #15

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.3359. Min Act: -0.1700

Data Index: 524690 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.3359. Min Act: -0.1700

Data Index: 208479 (C4 (Web Text))

Max Activating Token Index: 114

Text #17

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.3359. Min Act: -0.1700

Data Index: 758881 (C4 (Web Text))

Max Activating Token Index: 194

Text #18

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.2734. Min Act: -0.1700

Data Index: 381629 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 5.8047. Min Range: -5.8047

Max Act: 5.3203. Min Act: -0.1700

Data Index: 1160077 (C4 (Web Text))

Max Activating Token Index: 985