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

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

Neuron 931 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.2641. Min Range: -3.2641

Max Act: 3.2641. Min Act: -0.1700

Data Index: 30963 (C4 (Web Text))

Max Activating Token Index: 319

Text #1

Max Range: 3.2641. Min Range: -3.2641

Max Act: 3.2641. Min Act: -0.1700

Data Index: 1266875 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 3.2641. Min Range: -3.2641

Max Act: 3.2641. Min Act: -0.1700

Data Index: 483300 (C4 (Web Text))

Max Activating Token Index: 599

Text #3

Max Range: 3.2641. Min Range: -3.2641

Max Act: 3.2170. Min Act: -0.1700

Data Index: 679696 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 3.2641. Min Range: -3.2641

Max Act: 3.2012. Min Act: -0.1700

Data Index: 559065 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 3.2641. Min Range: -3.2641

Max Act: 3.2012. Min Act: -0.1700

Data Index: 1248427 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 3.2641. Min Range: -3.2641

Max Act: 3.1698. Min Act: -0.1700

Data Index: 1134530 (C4 (Web Text))

Max Activating Token Index: 408

Text #7

Max Range: 3.2641. Min Range: -3.2641

Max Act: 3.2170. Min Act: -0.1700

Data Index: 587591 (C4 (Web Text))

Max Activating Token Index: 512

Text #8

Max Range: 3.2641. Min Range: -3.2641

Max Act: 3.1855. Min Act: -0.1700

Data Index: 353448 (C4 (Web Text))

Max Activating Token Index: 456

Text #9

Max Range: 3.2641. Min Range: -3.2641

Max Act: 3.1225. Min Act: -0.1700

Data Index: 605802 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 3.2641. Min Range: -3.2641

Max Act: 3.0910. Min Act: -0.1700

Data Index: 658165 (C4 (Web Text))

Max Activating Token Index: 625

Text #11

Max Range: 3.2641. Min Range: -3.2641

Max Act: 3.1383. Min Act: -0.1700

Data Index: 525657 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 3.2641. Min Range: -3.2641

Max Act: 3.1225. Min Act: -0.1700

Data Index: 559509 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 3.2641. Min Range: -3.2641

Max Act: 3.1225. Min Act: -0.1700

Data Index: 964147 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 3.2641. Min Range: -3.2641

Max Act: 3.1067. Min Act: -0.1700

Data Index: 123075 (C4 (Web Text))

Max Activating Token Index: 775

Text #15

Max Range: 3.2641. Min Range: -3.2641

Max Act: 3.1067. Min Act: -0.1700

Data Index: 182470 (C4 (Web Text))

Max Activating Token Index: 309

Text #16

Max Range: 3.2641. Min Range: -3.2641

Max Act: 3.0910. Min Act: -0.1700

Data Index: 411673 (C4 (Web Text))

Max Activating Token Index: 941

Text #17

Max Range: 3.2641. Min Range: -3.2641

Max Act: 3.0910. Min Act: -0.1700

Data Index: 287916 (C4 (Web Text))

Max Activating Token Index: 242

Text #18

Max Range: 3.2641. Min Range: -3.2641

Max Act: 3.0910. Min Act: -0.1700

Data Index: 435884 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 3.2641. Min Range: -3.2641

Max Act: 3.0594. Min Act: -0.1700

Data Index: 259457 (C4 (Web Text))

Max Activating Token Index: 942