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

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

Neuron 1323 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: 3.1232. Min Range: -3.1232

Max Act: 3.1232. Min Act: -0.1700

Data Index: 245061 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 3.1232. Min Range: -3.1232

Max Act: 3.1232. Min Act: -0.1700

Data Index: 432400 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 3.1232. Min Range: -3.1232

Max Act: 3.1232. Min Act: -0.1700

Data Index: 1172401 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 3.1232. Min Range: -3.1232

Max Act: 3.1232. Min Act: -0.1700

Data Index: 789692 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 3.1232. Min Range: -3.1232

Max Act: 3.1075. Min Act: -0.1700

Data Index: 356488 (C4 (Web Text))

Max Activating Token Index: 992

Text #5

Max Range: 3.1232. Min Range: -3.1232

Max Act: 3.1075. Min Act: -0.1700

Data Index: 1183694 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 3.1232. Min Range: -3.1232

Max Act: 3.0917. Min Act: -0.1700

Data Index: 52677 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 3.1232. Min Range: -3.1232

Max Act: 3.0917. Min Act: -0.1700

Data Index: 289065 (C4 (Web Text))

Max Activating Token Index: 49

Text #8

Max Range: 3.1232. Min Range: -3.1232

Max Act: 3.0917. Min Act: -0.1700

Data Index: 1308977 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 3.1232. Min Range: -3.1232

Max Act: 3.0917. Min Act: -0.1700

Data Index: 324686 (C4 (Web Text))

Max Activating Token Index: 905

Text #10

Max Range: 3.1232. Min Range: -3.1232

Max Act: 3.0601. Min Act: -0.1700

Data Index: 289014 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 3.1232. Min Range: -3.1232

Max Act: 3.0759. Min Act: -0.1700

Data Index: 1046825 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 3.1232. Min Range: -3.1232

Max Act: 3.0601. Min Act: -0.1700

Data Index: 677848 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 3.1232. Min Range: -3.1232

Max Act: 3.0759. Min Act: -0.1700

Data Index: 1322362 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 3.1232. Min Range: -3.1232

Max Act: 3.0759. Min Act: -0.1700

Data Index: 26084 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 3.1232. Min Range: -3.1232

Max Act: 3.0759. Min Act: -0.1700

Data Index: 192260 (C4 (Web Text))

Max Activating Token Index: 275

Text #16

Max Range: 3.1232. Min Range: -3.1232

Max Act: 3.0601. Min Act: -0.1700

Data Index: 598035 (C4 (Web Text))

Max Activating Token Index: 733

Text #17

Max Range: 3.1232. Min Range: -3.1232

Max Act: 3.0601. Min Act: -0.1700

Data Index: 910053 (C4 (Web Text))

Max Activating Token Index: 94

Text #18

Max Range: 3.1232. Min Range: -3.1232

Max Act: 3.0601. Min Act: -0.1700

Data Index: 929167 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 3.1232. Min Range: -3.1232

Max Act: 3.0444. Min Act: -0.1700

Data Index: 606418 (C4 (Web Text))

Max Activating Token Index: 596