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

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

Neuron 840 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.1758. Min Range: -5.1758

Max Act: 5.0977. Min Act: -0.1700

Data Index: 561425 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 5.1758. Min Range: -5.1758

Max Act: 5.1758. Min Act: -0.1700

Data Index: 692862 (C4 (Web Text))

Max Activating Token Index: 268

Text #2

Max Range: 5.1758. Min Range: -5.1758

Max Act: 5.1133. Min Act: -0.1700

Data Index: 1315223 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 5.1758. Min Range: -5.1758

Max Act: 5.1290. Min Act: -0.1700

Data Index: 132456 (C4 (Web Text))

Max Activating Token Index: 377

Text #4

Max Range: 5.1758. Min Range: -5.1758

Max Act: 5.0977. Min Act: -0.1700

Data Index: 327295 (C4 (Web Text))

Max Activating Token Index: 522

Text #5

Max Range: 5.1758. Min Range: -5.1758

Max Act: 4.9883. Min Act: -0.1700

Data Index: 980268 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 5.1758. Min Range: -5.1758

Max Act: 4.9883. Min Act: -0.1700

Data Index: 1108884 (C4 (Web Text))

Max Activating Token Index: 109

Text #7

Max Range: 5.1758. Min Range: -5.1758

Max Act: 4.9258. Min Act: -0.1700

Data Index: 217846 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 5.1758. Min Range: -5.1758

Max Act: 4.9727. Min Act: -0.1700

Data Index: 845830 (C4 (Web Text))

Max Activating Token Index: 480

Text #9

Max Range: 5.1758. Min Range: -5.1758

Max Act: 4.9415. Min Act: -0.1700

Data Index: 773382 (C4 (Web Text))

Max Activating Token Index: 653

Text #10

Max Range: 5.1758. Min Range: -5.1758

Max Act: 5.0352. Min Act: -0.1700

Data Index: 700387 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 5.1758. Min Range: -5.1758

Max Act: 4.9415. Min Act: -0.1700

Data Index: 604955 (C4 (Web Text))

Max Activating Token Index: 616

Text #12

Max Range: 5.1758. Min Range: -5.1758

Max Act: 4.9102. Min Act: -0.1700

Data Index: 160265 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 5.1758. Min Range: -5.1758

Max Act: 5.0040. Min Act: -0.1700

Data Index: 136123 (C4 (Web Text))

Max Activating Token Index: 878

Text #14

Max Range: 5.1758. Min Range: -5.1758

Max Act: 4.8790. Min Act: -0.1700

Data Index: 303392 (C4 (Web Text))

Max Activating Token Index: 495

Text #15

Max Range: 5.1758. Min Range: -5.1758

Max Act: 4.8946. Min Act: -0.1700

Data Index: 582306 (C4 (Web Text))

Max Activating Token Index: 268

Text #16

Max Range: 5.1758. Min Range: -5.1758

Max Act: 4.8790. Min Act: -0.1700

Data Index: 1323966 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 5.1758. Min Range: -5.1758

Max Act: 4.8321. Min Act: -0.1700

Data Index: 1181185 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 5.1758. Min Range: -5.1758

Max Act: 4.8321. Min Act: -0.1700

Data Index: 730457 (C4 (Web Text))

Max Activating Token Index: 138

Text #19

Max Range: 5.1758. Min Range: -5.1758

Max Act: 4.8477. Min Act: -0.1700

Data Index: 608657 (C4 (Web Text))

Max Activating Token Index: 555