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

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

Neuron 1184 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: 5.3804. Min Range: -5.3804

Max Act: 5.3804. Min Act: -0.1700

Data Index: 741637 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 5.3804. Min Range: -5.3804

Max Act: 5.3491. Min Act: -0.1700

Data Index: 1124928 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 5.3804. Min Range: -5.3804

Max Act: 5.1929. Min Act: -0.1700

Data Index: 442381 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 5.3804. Min Range: -5.3804

Max Act: 5.1929. Min Act: -0.1700

Data Index: 434787 (C4 (Web Text))

Max Activating Token Index: 947

Text #4

Max Range: 5.3804. Min Range: -5.3804

Max Act: 5.2241. Min Act: -0.1700

Data Index: 418837 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 5.3804. Min Range: -5.3804

Max Act: 5.1616. Min Act: -0.1700

Data Index: 525645 (C4 (Web Text))

Max Activating Token Index: 981

Text #6

Max Range: 5.3804. Min Range: -5.3804

Max Act: 5.1304. Min Act: -0.1700

Data Index: 60578 (C4 (Web Text))

Max Activating Token Index: 994

Text #7

Max Range: 5.3804. Min Range: -5.3804

Max Act: 5.0679. Min Act: -0.1700

Data Index: 756342 (C4 (Web Text))

Max Activating Token Index: 1000

Text #8

Max Range: 5.3804. Min Range: -5.3804

Max Act: 5.0991. Min Act: -0.1700

Data Index: 1163945 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 5.3804. Min Range: -5.3804

Max Act: 5.0991. Min Act: -0.1700

Data Index: 355931 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 5.3804. Min Range: -5.3804

Max Act: 5.1304. Min Act: -0.1700

Data Index: 151852 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 5.3804. Min Range: -5.3804

Max Act: 5.0679. Min Act: -0.1700

Data Index: 1404030 (Python Code)

Max Activating Token Index: 152

Text #12

Max Range: 5.3804. Min Range: -5.3804

Max Act: 5.0679. Min Act: -0.1700

Data Index: 296298 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 5.3804. Min Range: -5.3804

Max Act: 5.0366. Min Act: -0.1700

Data Index: 895568 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 5.3804. Min Range: -5.3804

Max Act: 5.0054. Min Act: -0.1700

Data Index: 1420532 (Python Code)

Max Activating Token Index: 279

Text #15

Max Range: 5.3804. Min Range: -5.3804

Max Act: 4.9741. Min Act: -0.1700

Data Index: 1452370 (Python Code)

Max Activating Token Index: 761

Text #16

Max Range: 5.3804. Min Range: -5.3804

Max Act: 5.0366. Min Act: -0.1700

Data Index: 1326093 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 5.3804. Min Range: -5.3804

Max Act: 4.9116. Min Act: -0.1700

Data Index: 112631 (C4 (Web Text))

Max Activating Token Index: 560

Text #18

Max Range: 5.3804. Min Range: -5.3804

Max Act: 4.9741. Min Act: -0.1700

Data Index: 637766 (C4 (Web Text))

Max Activating Token Index: 685

Text #19

Max Range: 5.3804. Min Range: -5.3804

Max Act: 4.9429. Min Act: -0.1700

Data Index: 1241687 (C4 (Web Text))

Max Activating Token Index: 727