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

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

Neuron 1665 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: 3.3836. Min Range: -3.3836

Max Act: 3.3836. Min Act: -0.1700

Data Index: 1019655 (C4 (Web Text))

Max Activating Token Index: 142

Text #1

Max Range: 3.3836. Min Range: -3.3836

Max Act: 3.2737. Min Act: -0.1700

Data Index: 1182689 (C4 (Web Text))

Max Activating Token Index: 320

Text #2

Max Range: 3.3836. Min Range: -3.3836

Max Act: 3.2894. Min Act: -0.1700

Data Index: 938898 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 3.3836. Min Range: -3.3836

Max Act: 3.2580. Min Act: -0.1700

Data Index: 1342779 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 3.3836. Min Range: -3.3836

Max Act: 3.2265. Min Act: -0.1700

Data Index: 227757 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 3.3836. Min Range: -3.3836

Max Act: 3.2580. Min Act: -0.1700

Data Index: 471100 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 3.3836. Min Range: -3.3836

Max Act: 3.2423. Min Act: -0.1700

Data Index: 1016093 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 3.3836. Min Range: -3.3836

Max Act: 3.2265. Min Act: -0.1700

Data Index: 1176523 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 3.3836. Min Range: -3.3836

Max Act: 3.2423. Min Act: -0.1700

Data Index: 950167 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 3.3836. Min Range: -3.3836

Max Act: 3.1951. Min Act: -0.1700

Data Index: 841182 (C4 (Web Text))

Max Activating Token Index: 675

Text #10

Max Range: 3.3836. Min Range: -3.3836

Max Act: 3.2108. Min Act: -0.1700

Data Index: 812963 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 3.3836. Min Range: -3.3836

Max Act: 3.1951. Min Act: -0.1700

Data Index: 912451 (C4 (Web Text))

Max Activating Token Index: 349

Text #12

Max Range: 3.3836. Min Range: -3.3836

Max Act: 3.1951. Min Act: -0.1700

Data Index: 1271699 (C4 (Web Text))

Max Activating Token Index: 706

Text #13

Max Range: 3.3836. Min Range: -3.3836

Max Act: 3.1951. Min Act: -0.1700

Data Index: 20004 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 3.3836. Min Range: -3.3836

Max Act: 3.2423. Min Act: -0.1700

Data Index: 674127 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 3.3836. Min Range: -3.3836

Max Act: 3.1636. Min Act: -0.1700

Data Index: 457063 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 3.3836. Min Range: -3.3836

Max Act: 3.1951. Min Act: -0.1700

Data Index: 176003 (C4 (Web Text))

Max Activating Token Index: 692

Text #17

Max Range: 3.3836. Min Range: -3.3836

Max Act: 3.1479. Min Act: -0.1700

Data Index: 712953 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 3.3836. Min Range: -3.3836

Max Act: 3.1479. Min Act: -0.1700

Data Index: 529191 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 3.3836. Min Range: -3.3836

Max Act: 3.1636. Min Act: -0.1700

Data Index: 1237138 (C4 (Web Text))

Max Activating Token Index: 524