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

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

Neuron 1908 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: 5.1897. Min Range: -5.1897

Max Act: 5.1897. Min Act: -0.1700

Data Index: 69371 (C4 (Web Text))

Max Activating Token Index: 544

Text #1

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.9866. Min Act: -0.1700

Data Index: 813244 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.9241. Min Act: -0.1700

Data Index: 163195 (C4 (Web Text))

Max Activating Token Index: 784

Text #3

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.9397. Min Act: -0.1700

Data Index: 1046492 (C4 (Web Text))

Max Activating Token Index: 528

Text #4

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.8616. Min Act: -0.1700

Data Index: 789055 (C4 (Web Text))

Max Activating Token Index: 884

Text #5

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.8303. Min Act: -0.1700

Data Index: 597183 (C4 (Web Text))

Max Activating Token Index: 749

Text #6

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.8928. Min Act: -0.1700

Data Index: 574274 (C4 (Web Text))

Max Activating Token Index: 379

Text #7

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.7366. Min Act: -0.1700

Data Index: 1192138 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.7678. Min Act: -0.1700

Data Index: 1128371 (C4 (Web Text))

Max Activating Token Index: 708

Text #9

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.7991. Min Act: -0.1700

Data Index: 792302 (C4 (Web Text))

Max Activating Token Index: 1012

Text #10

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.7366. Min Act: -0.1700

Data Index: 985785 (C4 (Web Text))

Max Activating Token Index: 314

Text #11

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.7678. Min Act: -0.1700

Data Index: 1066106 (C4 (Web Text))

Max Activating Token Index: 176

Text #12

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.7366. Min Act: -0.1700

Data Index: 1182214 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.7366. Min Act: -0.1700

Data Index: 1194350 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.6584. Min Act: -0.1700

Data Index: 5101 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.6584. Min Act: -0.1700

Data Index: 1005112 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.6897. Min Act: -0.1700

Data Index: 164626 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.7366. Min Act: -0.1700

Data Index: 784458 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.6428. Min Act: -0.1700

Data Index: 486290 (C4 (Web Text))

Max Activating Token Index: 882

Text #19

Max Range: 5.1897. Min Range: -5.1897

Max Act: 4.6741. Min Act: -0.1700

Data Index: 353425 (C4 (Web Text))

Max Activating Token Index: 92