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

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

Neuron 595 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.7839. Min Range: -3.7839

Max Act: 3.7839. Min Act: -0.1700

Data Index: 346562 (C4 (Web Text))

Max Activating Token Index: 30

Text #1

Max Range: 3.7839. Min Range: -3.7839

Max Act: 3.6274. Min Act: -0.1700

Data Index: 1164120 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 3.7839. Min Range: -3.7839

Max Act: 3.5961. Min Act: -0.1700

Data Index: 435083 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 3.7839. Min Range: -3.7839

Max Act: 3.5804. Min Act: -0.1700

Data Index: 817828 (C4 (Web Text))

Max Activating Token Index: 124

Text #4

Max Range: 3.7839. Min Range: -3.7839

Max Act: 3.5961. Min Act: -0.1700

Data Index: 420165 (C4 (Web Text))

Max Activating Token Index: 583

Text #5

Max Range: 3.7839. Min Range: -3.7839

Max Act: 3.5648. Min Act: -0.1700

Data Index: 543704 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 3.7839. Min Range: -3.7839

Max Act: 3.5178. Min Act: -0.1700

Data Index: 345956 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 3.7839. Min Range: -3.7839

Max Act: 3.5335. Min Act: -0.1700

Data Index: 315865 (C4 (Web Text))

Max Activating Token Index: 923

Text #8

Max Range: 3.7839. Min Range: -3.7839

Max Act: 3.5335. Min Act: -0.1700

Data Index: 396491 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 3.7839. Min Range: -3.7839

Max Act: 3.5178. Min Act: -0.1700

Data Index: 252177 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 3.7839. Min Range: -3.7839

Max Act: 3.5178. Min Act: -0.1700

Data Index: 1095527 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 3.7839. Min Range: -3.7839

Max Act: 3.4708. Min Act: -0.1700

Data Index: 111562 (C4 (Web Text))

Max Activating Token Index: 868

Text #12

Max Range: 3.7839. Min Range: -3.7839

Max Act: 3.4865. Min Act: -0.1700

Data Index: 787924 (C4 (Web Text))

Max Activating Token Index: 460

Text #13

Max Range: 3.7839. Min Range: -3.7839

Max Act: 3.4865. Min Act: -0.1700

Data Index: 21650 (C4 (Web Text))

Max Activating Token Index: 83

Text #14

Max Range: 3.7839. Min Range: -3.7839

Max Act: 3.5021. Min Act: -0.1700

Data Index: 1145688 (C4 (Web Text))

Max Activating Token Index: 1012

Text #15

Max Range: 3.7839. Min Range: -3.7839

Max Act: 3.4708. Min Act: -0.1700

Data Index: 673770 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 3.7839. Min Range: -3.7839

Max Act: 3.4865. Min Act: -0.1700

Data Index: 500504 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 3.7839. Min Range: -3.7839

Max Act: 3.4551. Min Act: -0.1700

Data Index: 662136 (C4 (Web Text))

Max Activating Token Index: 704

Text #18

Max Range: 3.7839. Min Range: -3.7839

Max Act: 3.4708. Min Act: -0.1700

Data Index: 1081668 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 3.7839. Min Range: -3.7839

Max Act: 3.4708. Min Act: -0.1700

Data Index: 1043484 (C4 (Web Text))

Max Activating Token Index: 568