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

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

Neuron 1792 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: 5.8891. Min Range: -5.8891

Max Act: 5.8891. Min Act: -0.1700

Data Index: 1163518 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 5.8891. Min Range: -5.8891

Max Act: 5.8579. Min Act: -0.1700

Data Index: 1022114 (C4 (Web Text))

Max Activating Token Index: 152

Text #2

Max Range: 5.8891. Min Range: -5.8891

Max Act: 5.7329. Min Act: -0.1700

Data Index: 156294 (C4 (Web Text))

Max Activating Token Index: 938

Text #3

Max Range: 5.8891. Min Range: -5.8891

Max Act: 5.7641. Min Act: -0.1700

Data Index: 672329 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 5.8891. Min Range: -5.8891

Max Act: 5.7016. Min Act: -0.1700

Data Index: 539230 (C4 (Web Text))

Max Activating Token Index: 324

Text #5

Max Range: 5.8891. Min Range: -5.8891

Max Act: 5.6391. Min Act: -0.1700

Data Index: 1230405 (C4 (Web Text))

Max Activating Token Index: 223

Text #6

Max Range: 5.8891. Min Range: -5.8891

Max Act: 5.6079. Min Act: -0.1700

Data Index: 580398 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 5.8891. Min Range: -5.8891

Max Act: 5.6079. Min Act: -0.1700

Data Index: 1228756 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 5.8891. Min Range: -5.8891

Max Act: 5.5454. Min Act: -0.1700

Data Index: 253534 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 5.8891. Min Range: -5.8891

Max Act: 5.6079. Min Act: -0.1700

Data Index: 248913 (C4 (Web Text))

Max Activating Token Index: 484

Text #10

Max Range: 5.8891. Min Range: -5.8891

Max Act: 5.5454. Min Act: -0.1700

Data Index: 927534 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 5.8891. Min Range: -5.8891

Max Act: 5.5766. Min Act: -0.1700

Data Index: 224920 (C4 (Web Text))

Max Activating Token Index: 651

Text #12

Max Range: 5.8891. Min Range: -5.8891

Max Act: 5.5141. Min Act: -0.1700

Data Index: 524608 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 5.8891. Min Range: -5.8891

Max Act: 5.4829. Min Act: -0.1700

Data Index: 1038459 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 5.8891. Min Range: -5.8891

Max Act: 5.5454. Min Act: -0.1700

Data Index: 294073 (C4 (Web Text))

Max Activating Token Index: 1015

Text #15

Max Range: 5.8891. Min Range: -5.8891

Max Act: 5.4829. Min Act: -0.1700

Data Index: 863367 (C4 (Web Text))

Max Activating Token Index: 955

Text #16

Max Range: 5.8891. Min Range: -5.8891

Max Act: 5.4829. Min Act: -0.1700

Data Index: 666422 (C4 (Web Text))

Max Activating Token Index: 1010

Text #17

Max Range: 5.8891. Min Range: -5.8891

Max Act: 5.4516. Min Act: -0.1700

Data Index: 344832 (C4 (Web Text))

Max Activating Token Index: 129

Text #18

Max Range: 5.8891. Min Range: -5.8891

Max Act: 5.4829. Min Act: -0.1700

Data Index: 229433 (C4 (Web Text))

Max Activating Token Index: 909

Text #19

Max Range: 5.8891. Min Range: -5.8891

Max Act: 5.4516. Min Act: -0.1700

Data Index: 186921 (C4 (Web Text))

Max Activating Token Index: 131