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

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

Neuron 159 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: 5.5638. Min Range: -5.5638

Max Act: 5.5638. Min Act: -0.1700

Data Index: 311180 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 5.5638. Min Range: -5.5638

Max Act: 5.4076. Min Act: -0.1699

Data Index: 641735 (C4 (Web Text))

Max Activating Token Index: 181

Text #2

Max Range: 5.5638. Min Range: -5.5638

Max Act: 5.3763. Min Act: -0.1700

Data Index: 1216169 (C4 (Web Text))

Max Activating Token Index: 81

Text #3

Max Range: 5.5638. Min Range: -5.5638

Max Act: 5.4076. Min Act: -0.1700

Data Index: 1172969 (C4 (Web Text))

Max Activating Token Index: 609

Text #4

Max Range: 5.5638. Min Range: -5.5638

Max Act: 5.3450. Min Act: -0.1700

Data Index: 1240753 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 5.5638. Min Range: -5.5638

Max Act: 5.2825. Min Act: -0.1700

Data Index: 1170527 (C4 (Web Text))

Max Activating Token Index: 184

Text #6

Max Range: 5.5638. Min Range: -5.5638

Max Act: 5.3138. Min Act: -0.1700

Data Index: 570550 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 5.5638. Min Range: -5.5638

Max Act: 5.2825. Min Act: -0.1700

Data Index: 714638 (C4 (Web Text))

Max Activating Token Index: 178

Text #8

Max Range: 5.5638. Min Range: -5.5638

Max Act: 5.2825. Min Act: -0.1700

Data Index: 928028 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 5.5638. Min Range: -5.5638

Max Act: 5.3138. Min Act: -0.1700

Data Index: 628129 (C4 (Web Text))

Max Activating Token Index: 459

Text #10

Max Range: 5.5638. Min Range: -5.5638

Max Act: 5.3450. Min Act: -0.1700

Data Index: 314962 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 5.5638. Min Range: -5.5638

Max Act: 5.2513. Min Act: -0.1700

Data Index: 978083 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 5.5638. Min Range: -5.5638

Max Act: 5.2513. Min Act: -0.1700

Data Index: 1085516 (C4 (Web Text))

Max Activating Token Index: 121

Text #13

Max Range: 5.5638. Min Range: -5.5638

Max Act: 5.2825. Min Act: -0.1700

Data Index: 645989 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 5.5638. Min Range: -5.5638

Max Act: 5.2825. Min Act: -0.1700

Data Index: 519281 (C4 (Web Text))

Max Activating Token Index: 636

Text #15

Max Range: 5.5638. Min Range: -5.5638

Max Act: 5.2200. Min Act: -0.1700

Data Index: 1138692 (C4 (Web Text))

Max Activating Token Index: 156

Text #16

Max Range: 5.5638. Min Range: -5.5638

Max Act: 5.2200. Min Act: -0.1700

Data Index: 839124 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 5.5638. Min Range: -5.5638

Max Act: 5.2200. Min Act: -0.1700

Data Index: 854908 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 5.5638. Min Range: -5.5638

Max Act: 5.2200. Min Act: -0.1700

Data Index: 1168780 (C4 (Web Text))

Max Activating Token Index: 919

Text #19

Max Range: 5.5638. Min Range: -5.5638

Max Act: 5.2513. Min Act: -0.1700

Data Index: 341528 (C4 (Web Text))

Max Activating Token Index: 280