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

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

Neuron 1894 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: 5.2112. Min Range: -5.2112

Max Act: 5.2112. Min Act: -0.1700

Data Index: 374139 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 5.2112. Min Range: -5.2112

Max Act: 5.1800. Min Act: -0.1700

Data Index: 128869 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 5.2112. Min Range: -5.2112

Max Act: 5.1487. Min Act: -0.1700

Data Index: 1242191 (C4 (Web Text))

Max Activating Token Index: 25

Text #3

Max Range: 5.2112. Min Range: -5.2112

Max Act: 5.1487. Min Act: -0.1700

Data Index: 607645 (C4 (Web Text))

Max Activating Token Index: 100

Text #4

Max Range: 5.2112. Min Range: -5.2112

Max Act: 5.1175. Min Act: -0.1700

Data Index: 947275 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 5.2112. Min Range: -5.2112

Max Act: 5.1175. Min Act: -0.1700

Data Index: 673184 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 5.2112. Min Range: -5.2112

Max Act: 5.1175. Min Act: -0.1700

Data Index: 377830 (C4 (Web Text))

Max Activating Token Index: 888

Text #7

Max Range: 5.2112. Min Range: -5.2112

Max Act: 5.0862. Min Act: -0.1700

Data Index: 1343993 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 5.2112. Min Range: -5.2112

Max Act: 5.0550. Min Act: -0.1700

Data Index: 377757 (C4 (Web Text))

Max Activating Token Index: 85

Text #9

Max Range: 5.2112. Min Range: -5.2112

Max Act: 5.0862. Min Act: -0.1700

Data Index: 174756 (C4 (Web Text))

Max Activating Token Index: 624

Text #10

Max Range: 5.2112. Min Range: -5.2112

Max Act: 5.0237. Min Act: -0.1700

Data Index: 1302809 (C4 (Web Text))

Max Activating Token Index: 467

Text #11

Max Range: 5.2112. Min Range: -5.2112

Max Act: 5.0550. Min Act: -0.1700

Data Index: 899504 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 5.2112. Min Range: -5.2112

Max Act: 5.0237. Min Act: -0.1700

Data Index: 851542 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 5.2112. Min Range: -5.2112

Max Act: 5.0550. Min Act: -0.1700

Data Index: 751356 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 5.2112. Min Range: -5.2112

Max Act: 5.0237. Min Act: -0.1700

Data Index: 1238451 (C4 (Web Text))

Max Activating Token Index: 210

Text #15

Max Range: 5.2112. Min Range: -5.2112

Max Act: 5.0550. Min Act: -0.1700

Data Index: 616774 (C4 (Web Text))

Max Activating Token Index: 588

Text #16

Max Range: 5.2112. Min Range: -5.2112

Max Act: 4.9925. Min Act: -0.1700

Data Index: 684397 (C4 (Web Text))

Max Activating Token Index: 750

Text #17

Max Range: 5.2112. Min Range: -5.2112

Max Act: 5.0550. Min Act: -0.1700

Data Index: 1174475 (C4 (Web Text))

Max Activating Token Index: 878

Text #18

Max Range: 5.2112. Min Range: -5.2112

Max Act: 5.0237. Min Act: -0.1700

Data Index: 765156 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 5.2112. Min Range: -5.2112

Max Act: 5.0550. Min Act: -0.1700

Data Index: 597481 (C4 (Web Text))

Max Activating Token Index: 657