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

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

Neuron 1875 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: 3.1066. Min Range: -3.1066

Max Act: 3.1066. Min Act: -0.1700

Data Index: 63451 (C4 (Web Text))

Max Activating Token Index: 613

Text #1

Max Range: 3.1066. Min Range: -3.1066

Max Act: 3.0909. Min Act: -0.1700

Data Index: 159879 (C4 (Web Text))

Max Activating Token Index: 412

Text #2

Max Range: 3.1066. Min Range: -3.1066

Max Act: 2.9961. Min Act: -0.1700

Data Index: 551379 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 3.1066. Min Range: -3.1066

Max Act: 2.9328. Min Act: -0.1700

Data Index: 500271 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 3.1066. Min Range: -3.1066

Max Act: 2.9328. Min Act: -0.1700

Data Index: 830392 (C4 (Web Text))

Max Activating Token Index: 903

Text #5

Max Range: 3.1066. Min Range: -3.1066

Max Act: 2.8852. Min Act: -0.1700

Data Index: 582982 (C4 (Web Text))

Max Activating Token Index: 437

Text #6

Max Range: 3.1066. Min Range: -3.1066

Max Act: 2.9170. Min Act: -0.1700

Data Index: 544896 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 3.1066. Min Range: -3.1066

Max Act: 2.9328. Min Act: -0.1700

Data Index: 606388 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 3.1066. Min Range: -3.1066

Max Act: 2.9011. Min Act: -0.1700

Data Index: 848953 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 3.1066. Min Range: -3.1066

Max Act: 2.9011. Min Act: -0.1700

Data Index: 1046515 (C4 (Web Text))

Max Activating Token Index: 921

Text #10

Max Range: 3.1066. Min Range: -3.1066

Max Act: 2.8852. Min Act: -0.1700

Data Index: 1175066 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 3.1066. Min Range: -3.1066

Max Act: 2.8852. Min Act: -0.1700

Data Index: 1280031 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 3.1066. Min Range: -3.1066

Max Act: 2.8852. Min Act: -0.1700

Data Index: 159631 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 3.1066. Min Range: -3.1066

Max Act: 2.8852. Min Act: -0.1700

Data Index: 35724 (C4 (Web Text))

Max Activating Token Index: 519

Text #14

Max Range: 3.1066. Min Range: -3.1066

Max Act: 2.8694. Min Act: -0.1700

Data Index: 133011 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 3.1066. Min Range: -3.1066

Max Act: 2.8535. Min Act: -0.1700

Data Index: 778777 (C4 (Web Text))

Max Activating Token Index: 111

Text #16

Max Range: 3.1066. Min Range: -3.1066

Max Act: 2.8376. Min Act: -0.1700

Data Index: 342942 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 3.1066. Min Range: -3.1066

Max Act: 2.8694. Min Act: -0.1700

Data Index: 338244 (C4 (Web Text))

Max Activating Token Index: 126

Text #18

Max Range: 3.1066. Min Range: -3.1066

Max Act: 2.8376. Min Act: -0.1700

Data Index: 557914 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 3.1066. Min Range: -3.1066

Max Act: 2.8376. Min Act: -0.1700

Data Index: 367109 (C4 (Web Text))

Max Activating Token Index: 183