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

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

Neuron 1708 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: 5.3778. Min Range: -5.3778

Max Act: 5.3778. Min Act: -0.1700

Data Index: 1236275 (C4 (Web Text))

Max Activating Token Index: 133

Text #1

Max Range: 5.3778. Min Range: -5.3778

Max Act: 5.3466. Min Act: -0.1700

Data Index: 1258977 (C4 (Web Text))

Max Activating Token Index: 720

Text #2

Max Range: 5.3778. Min Range: -5.3778

Max Act: 5.2216. Min Act: -0.1700

Data Index: 1021450 (C4 (Web Text))

Max Activating Token Index: 855

Text #3

Max Range: 5.3778. Min Range: -5.3778

Max Act: 5.1903. Min Act: -0.1700

Data Index: 890014 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 5.3778. Min Range: -5.3778

Max Act: 5.1903. Min Act: -0.1699

Data Index: 311158 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 5.3778. Min Range: -5.3778

Max Act: 5.1903. Min Act: -0.1700

Data Index: 1164622 (C4 (Web Text))

Max Activating Token Index: 149

Text #6

Max Range: 5.3778. Min Range: -5.3778

Max Act: 5.1591. Min Act: -0.1700

Data Index: 349870 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 5.3778. Min Range: -5.3778

Max Act: 5.1278. Min Act: -0.1700

Data Index: 1207553 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 5.3778. Min Range: -5.3778

Max Act: 5.1591. Min Act: -0.1700

Data Index: 1317748 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 5.3778. Min Range: -5.3778

Max Act: 5.1591. Min Act: -0.1700

Data Index: 341812 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 5.3778. Min Range: -5.3778

Max Act: 5.1278. Min Act: -0.1700

Data Index: 431975 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 5.3778. Min Range: -5.3778

Max Act: 5.1278. Min Act: -0.1700

Data Index: 851588 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 5.3778. Min Range: -5.3778

Max Act: 5.0966. Min Act: -0.1700

Data Index: 425823 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 5.3778. Min Range: -5.3778

Max Act: 5.1591. Min Act: -0.1700

Data Index: 419857 (C4 (Web Text))

Max Activating Token Index: 182

Text #14

Max Range: 5.3778. Min Range: -5.3778

Max Act: 5.1278. Min Act: -0.1700

Data Index: 158562 (C4 (Web Text))

Max Activating Token Index: 160

Text #15

Max Range: 5.3778. Min Range: -5.3778

Max Act: 5.1278. Min Act: -0.1700

Data Index: 485197 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 5.3778. Min Range: -5.3778

Max Act: 5.0966. Min Act: -0.1700

Data Index: 370161 (C4 (Web Text))

Max Activating Token Index: 120

Text #17

Max Range: 5.3778. Min Range: -5.3778

Max Act: 5.0966. Min Act: -0.1699

Data Index: 758679 (C4 (Web Text))

Max Activating Token Index: 118

Text #18

Max Range: 5.3778. Min Range: -5.3778

Max Act: 5.1278. Min Act: -0.1700

Data Index: 340450 (C4 (Web Text))

Max Activating Token Index: 86

Text #19

Max Range: 5.3778. Min Range: -5.3778

Max Act: 5.0653. Min Act: -0.1700

Data Index: 208999 (C4 (Web Text))

Max Activating Token Index: 606