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

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

Neuron 1087 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.8194. Min Act: -0.1700

Data Index: 1294423 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.8038. Min Act: -0.1700

Data Index: 1020909 (C4 (Web Text))

Max Activating Token Index: 624

Text #2

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.7412. Min Act: -0.1700

Data Index: 1248123 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.8038. Min Act: -0.1700

Data Index: 34691 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.7568. Min Act: -0.1700

Data Index: 840902 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.7725. Min Act: -0.1700

Data Index: 1307864 (C4 (Web Text))

Max Activating Token Index: 518

Text #6

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.7412. Min Act: -0.1700

Data Index: 235882 (C4 (Web Text))

Max Activating Token Index: 661

Text #7

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.7568. Min Act: -0.1700

Data Index: 903581 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.7568. Min Act: -0.1700

Data Index: 446755 (C4 (Web Text))

Max Activating Token Index: 961

Text #9

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.7881. Min Act: -0.1700

Data Index: 95874 (C4 (Web Text))

Max Activating Token Index: 274

Text #10

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.7725. Min Act: -0.1700

Data Index: 674514 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.7725. Min Act: -0.1700

Data Index: 974943 (C4 (Web Text))

Max Activating Token Index: 735

Text #12

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.7568. Min Act: -0.1700

Data Index: 36724 (C4 (Web Text))

Max Activating Token Index: 826

Text #13

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.7725. Min Act: -0.1700

Data Index: 113694 (C4 (Web Text))

Max Activating Token Index: 520

Text #14

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.7412. Min Act: -0.1700

Data Index: 916112 (C4 (Web Text))

Max Activating Token Index: 735

Text #15

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.7568. Min Act: -0.1700

Data Index: 1234181 (C4 (Web Text))

Max Activating Token Index: 655

Text #16

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.7725. Min Act: -0.1700

Data Index: 1225509 (C4 (Web Text))

Max Activating Token Index: 271

Text #17

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.7255. Min Act: -0.1700

Data Index: 442975 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.7412. Min Act: -0.1700

Data Index: 612044 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 3.8194. Min Range: -3.8194

Max Act: 3.7412. Min Act: -0.1700

Data Index: 938242 (C4 (Web Text))

Max Activating Token Index: 338