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

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

Neuron 622 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: 3.6146. Min Range: -3.6146

Max Act: 3.6146. Min Act: -0.1700

Data Index: 1069790 (C4 (Web Text))

Max Activating Token Index: 812

Text #1

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.5832. Min Act: -0.1700

Data Index: 738242 (C4 (Web Text))

Max Activating Token Index: 791

Text #2

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.5832. Min Act: -0.1700

Data Index: 1218176 (C4 (Web Text))

Max Activating Token Index: 633

Text #3

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.5519. Min Act: -0.1700

Data Index: 584789 (C4 (Web Text))

Max Activating Token Index: 874

Text #4

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.5676. Min Act: -0.1700

Data Index: 324264 (C4 (Web Text))

Max Activating Token Index: 178

Text #5

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.5363. Min Act: -0.1700

Data Index: 332908 (C4 (Web Text))

Max Activating Token Index: 185

Text #6

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.5363. Min Act: -0.1700

Data Index: 142553 (C4 (Web Text))

Max Activating Token Index: 550

Text #7

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.5676. Min Act: -0.1700

Data Index: 855146 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.5206. Min Act: -0.1700

Data Index: 542021 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.5363. Min Act: -0.1700

Data Index: 236274 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.5206. Min Act: -0.1700

Data Index: 846179 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.5206. Min Act: -0.1700

Data Index: 72596 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.5049. Min Act: -0.1700

Data Index: 748796 (C4 (Web Text))

Max Activating Token Index: 602

Text #13

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.5363. Min Act: -0.1700

Data Index: 563142 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.5049. Min Act: -0.1700

Data Index: 1142933 (C4 (Web Text))

Max Activating Token Index: 131

Text #15

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.5206. Min Act: -0.1700

Data Index: 26371 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.5206. Min Act: -0.1700

Data Index: 1243720 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.5363. Min Act: -0.1700

Data Index: 1239682 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.4893. Min Act: -0.1700

Data Index: 665337 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 3.6146. Min Range: -3.6146

Max Act: 3.5049. Min Act: -0.1700

Data Index: 628065 (C4 (Web Text))

Max Activating Token Index: 249