Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1595 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.9856. Min Act: -0.1700

Data Index: 1126990 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.9387. Min Act: -0.1700

Data Index: 252446 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.8918. Min Act: -0.1700

Data Index: 1142411 (C4 (Web Text))

Max Activating Token Index: 337

Text #3

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.8449. Min Act: -0.1700

Data Index: 1337445 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.7980. Min Act: -0.1700

Data Index: 667127 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.7824. Min Act: -0.1700

Data Index: 739706 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.7667. Min Act: -0.1700

Data Index: 191081 (C4 (Web Text))

Max Activating Token Index: 350

Text #7

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.7824. Min Act: -0.1700

Data Index: 424543 (C4 (Web Text))

Max Activating Token Index: 779

Text #8

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.7667. Min Act: -0.1700

Data Index: 560924 (C4 (Web Text))

Max Activating Token Index: 551

Text #9

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.7511. Min Act: -0.1700

Data Index: 389081 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.7511. Min Act: -0.1700

Data Index: 4898 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.7667. Min Act: -0.1700

Data Index: 63595 (C4 (Web Text))

Max Activating Token Index: 17

Text #12

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.7198. Min Act: -0.1700

Data Index: 543606 (C4 (Web Text))

Max Activating Token Index: 102

Text #13

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.7511. Min Act: -0.1700

Data Index: 1178010 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.7198. Min Act: -0.1700

Data Index: 218379 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.7354. Min Act: -0.1700

Data Index: 548214 (C4 (Web Text))

Max Activating Token Index: 568

Text #16

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.7354. Min Act: -0.1700

Data Index: 645867 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.7354. Min Act: -0.1700

Data Index: 1021512 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.7354. Min Act: -0.1700

Data Index: 1063966 (C4 (Web Text))

Max Activating Token Index: 414

Text #19

Max Range: 3.9856. Min Range: -3.9856

Max Act: 3.6885. Min Act: -0.1700

Data Index: 1228277 (C4 (Web Text))

Max Activating Token Index: 106