Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1081 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.1744. Min Range: -5.1744

Max Act: 5.1744. Min Act: -0.1700

Data Index: 1158878 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 5.1744. Min Range: -5.1744

Max Act: 5.1119. Min Act: -0.1700

Data Index: 1042860 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 5.1744. Min Range: -5.1744

Max Act: 5.0494. Min Act: -0.1700

Data Index: 405693 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 5.1744. Min Range: -5.1744

Max Act: 5.0181. Min Act: -0.1700

Data Index: 1312187 (C4 (Web Text))

Max Activating Token Index: 620

Text #4

Max Range: 5.1744. Min Range: -5.1744

Max Act: 5.0494. Min Act: -0.1700

Data Index: 904637 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 5.1744. Min Range: -5.1744

Max Act: 5.0494. Min Act: -0.1700

Data Index: 746956 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 5.1744. Min Range: -5.1744

Max Act: 5.0181. Min Act: -0.1700

Data Index: 1136263 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 5.1744. Min Range: -5.1744

Max Act: 5.0181. Min Act: -0.1700

Data Index: 1013242 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 5.1744. Min Range: -5.1744

Max Act: 4.9869. Min Act: -0.1700

Data Index: 767413 (C4 (Web Text))

Max Activating Token Index: 286

Text #9

Max Range: 5.1744. Min Range: -5.1744

Max Act: 4.9556. Min Act: -0.1700

Data Index: 1175661 (C4 (Web Text))

Max Activating Token Index: 651

Text #10

Max Range: 5.1744. Min Range: -5.1744

Max Act: 4.9556. Min Act: -0.1700

Data Index: 793003 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 5.1744. Min Range: -5.1744

Max Act: 4.8306. Min Act: -0.1700

Data Index: 970916 (C4 (Web Text))

Max Activating Token Index: 995

Text #12

Max Range: 5.1744. Min Range: -5.1744

Max Act: 4.8306. Min Act: -0.1700

Data Index: 227207 (C4 (Web Text))

Max Activating Token Index: 982

Text #13

Max Range: 5.1744. Min Range: -5.1744

Max Act: 4.8619. Min Act: -0.1700

Data Index: 425336 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 5.1744. Min Range: -5.1744

Max Act: 4.7994. Min Act: -0.1700

Data Index: 1080291 (C4 (Web Text))

Max Activating Token Index: 978

Text #15

Max Range: 5.1744. Min Range: -5.1744

Max Act: 4.7994. Min Act: -0.1700

Data Index: 1080755 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 5.1744. Min Range: -5.1744

Max Act: 4.8306. Min Act: -0.1700

Data Index: 1117394 (C4 (Web Text))

Max Activating Token Index: 292

Text #17

Max Range: 5.1744. Min Range: -5.1744

Max Act: 4.7681. Min Act: -0.1700

Data Index: 768585 (C4 (Web Text))

Max Activating Token Index: 857

Text #18

Max Range: 5.1744. Min Range: -5.1744

Max Act: 4.7994. Min Act: -0.1700

Data Index: 283043 (C4 (Web Text))

Max Activating Token Index: 903

Text #19

Max Range: 5.1744. Min Range: -5.1744

Max Act: 4.7994. Min Act: -0.1700

Data Index: 649822 (C4 (Web Text))

Max Activating Token Index: 498