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

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

Neuron 1431 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: 3.4727. Min Range: -3.4727

Max Act: 3.4727. Min Act: -0.1700

Data Index: 788846 (C4 (Web Text))

Max Activating Token Index: 798

Text #1

Max Range: 3.4727. Min Range: -3.4727

Max Act: 3.2372. Min Act: -0.1700

Data Index: 138862 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 3.4727. Min Range: -3.4727

Max Act: 3.1901. Min Act: -0.1700

Data Index: 914636 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 3.4727. Min Range: -3.4727

Max Act: 3.1743. Min Act: -0.1700

Data Index: 1069703 (C4 (Web Text))

Max Activating Token Index: 587

Text #4

Max Range: 3.4727. Min Range: -3.4727

Max Act: 3.1586. Min Act: -0.1700

Data Index: 153181 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 3.4727. Min Range: -3.4727

Max Act: 3.1271. Min Act: -0.1700

Data Index: 1265137 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 3.4727. Min Range: -3.4727

Max Act: 3.1113. Min Act: -0.1700

Data Index: 1312628 (C4 (Web Text))

Max Activating Token Index: 1012

Text #7

Max Range: 3.4727. Min Range: -3.4727

Max Act: 3.0955. Min Act: -0.1700

Data Index: 1172691 (C4 (Web Text))

Max Activating Token Index: 106

Text #8

Max Range: 3.4727. Min Range: -3.4727

Max Act: 3.0798. Min Act: -0.1700

Data Index: 1346873 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 3.4727. Min Range: -3.4727

Max Act: 3.0798. Min Act: -0.1700

Data Index: 172732 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 3.4727. Min Range: -3.4727

Max Act: 3.0482. Min Act: -0.1700

Data Index: 231219 (C4 (Web Text))

Max Activating Token Index: 32

Text #11

Max Range: 3.4727. Min Range: -3.4727

Max Act: 3.0640. Min Act: -0.1700

Data Index: 976819 (C4 (Web Text))

Max Activating Token Index: 845

Text #12

Max Range: 3.4727. Min Range: -3.4727

Max Act: 3.0798. Min Act: -0.1700

Data Index: 371314 (C4 (Web Text))

Max Activating Token Index: 817

Text #13

Max Range: 3.4727. Min Range: -3.4727

Max Act: 3.0482. Min Act: -0.1700

Data Index: 655793 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 3.4727. Min Range: -3.4727

Max Act: 3.0482. Min Act: -0.1700

Data Index: 590990 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 3.4727. Min Range: -3.4727

Max Act: 3.0324. Min Act: -0.1700

Data Index: 354127 (C4 (Web Text))

Max Activating Token Index: 689

Text #16

Max Range: 3.4727. Min Range: -3.4727

Max Act: 3.0482. Min Act: -0.1700

Data Index: 476126 (C4 (Web Text))

Max Activating Token Index: 116

Text #17

Max Range: 3.4727. Min Range: -3.4727

Max Act: 3.0008. Min Act: -0.1700

Data Index: 1030439 (C4 (Web Text))

Max Activating Token Index: 398

Text #18

Max Range: 3.4727. Min Range: -3.4727

Max Act: 3.0166. Min Act: -0.1700

Data Index: 1150434 (C4 (Web Text))

Max Activating Token Index: 265

Text #19

Max Range: 3.4727. Min Range: -3.4727

Max Act: 3.0008. Min Act: -0.1700

Data Index: 1179312 (C4 (Web Text))

Max Activating Token Index: 1011