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

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

Neuron 706 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.3188. Min Range: -3.3188

Max Act: 3.3188. Min Act: -0.1700

Data Index: 476798 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 3.3188. Min Range: -3.3188

Max Act: 3.1458. Min Act: -0.1700

Data Index: 933372 (C4 (Web Text))

Max Activating Token Index: 924

Text #2

Max Range: 3.3188. Min Range: -3.3188

Max Act: 3.1143. Min Act: -0.1700

Data Index: 197699 (C4 (Web Text))

Max Activating Token Index: 364

Text #3

Max Range: 3.3188. Min Range: -3.3188

Max Act: 3.1143. Min Act: -0.1700

Data Index: 170918 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 3.3188. Min Range: -3.3188

Max Act: 3.0985. Min Act: -0.1700

Data Index: 969888 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 3.3188. Min Range: -3.3188

Max Act: 3.0828. Min Act: -0.1700

Data Index: 1156171 (C4 (Web Text))

Max Activating Token Index: 428

Text #6

Max Range: 3.3188. Min Range: -3.3188

Max Act: 3.0985. Min Act: -0.1700

Data Index: 988748 (C4 (Web Text))

Max Activating Token Index: 79

Text #7

Max Range: 3.3188. Min Range: -3.3188

Max Act: 3.0670. Min Act: -0.1700

Data Index: 69793 (C4 (Web Text))

Max Activating Token Index: 799

Text #8

Max Range: 3.3188. Min Range: -3.3188

Max Act: 3.0512. Min Act: -0.1700

Data Index: 523606 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 3.3188. Min Range: -3.3188

Max Act: 3.0512. Min Act: -0.1700

Data Index: 1280866 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 3.3188. Min Range: -3.3188

Max Act: 3.0512. Min Act: -0.1700

Data Index: 1122325 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 3.3188. Min Range: -3.3188

Max Act: 3.0512. Min Act: -0.1700

Data Index: 742886 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 3.3188. Min Range: -3.3188

Max Act: 3.0354. Min Act: -0.1700

Data Index: 1197054 (C4 (Web Text))

Max Activating Token Index: 471

Text #13

Max Range: 3.3188. Min Range: -3.3188

Max Act: 3.0196. Min Act: -0.1700

Data Index: 829050 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 3.3188. Min Range: -3.3188

Max Act: 3.0196. Min Act: -0.1700

Data Index: 47159 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 3.3188. Min Range: -3.3188

Max Act: 3.0354. Min Act: -0.1700

Data Index: 1143412 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 3.3188. Min Range: -3.3188

Max Act: 3.0354. Min Act: -0.1700

Data Index: 89043 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 3.3188. Min Range: -3.3188

Max Act: 3.0196. Min Act: -0.1700

Data Index: 1169480 (C4 (Web Text))

Max Activating Token Index: 105

Text #18

Max Range: 3.3188. Min Range: -3.3188

Max Act: 3.0196. Min Act: -0.1700

Data Index: 831923 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 3.3188. Min Range: -3.3188

Max Act: 3.0196. Min Act: -0.1700

Data Index: 236917 (C4 (Web Text))

Max Activating Token Index: 928