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

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

Neuron 2030 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1925. Min Range: -5.1925

Max Act: 5.1925. Min Act: -0.1700

Data Index: 1265103 (C4 (Web Text))

Max Activating Token Index: 633

Text #1

Max Range: 5.1925. Min Range: -5.1925

Max Act: 5.1613. Min Act: -0.1700

Data Index: 398696 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 5.1925. Min Range: -5.1925

Max Act: 5.1300. Min Act: -0.1700

Data Index: 105586 (C4 (Web Text))

Max Activating Token Index: 653

Text #3

Max Range: 5.1925. Min Range: -5.1925

Max Act: 5.1613. Min Act: -0.1700

Data Index: 347028 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 5.1925. Min Range: -5.1925

Max Act: 5.1613. Min Act: -0.1700

Data Index: 610239 (C4 (Web Text))

Max Activating Token Index: 225

Text #5

Max Range: 5.1925. Min Range: -5.1925

Max Act: 5.1300. Min Act: -0.1700

Data Index: 82036 (C4 (Web Text))

Max Activating Token Index: 697

Text #6

Max Range: 5.1925. Min Range: -5.1925

Max Act: 5.0988. Min Act: -0.1700

Data Index: 40559 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 5.1925. Min Range: -5.1925

Max Act: 5.1300. Min Act: -0.1700

Data Index: 298381 (C4 (Web Text))

Max Activating Token Index: 948

Text #8

Max Range: 5.1925. Min Range: -5.1925

Max Act: 5.0988. Min Act: -0.1700

Data Index: 456325 (C4 (Web Text))

Max Activating Token Index: 844

Text #9

Max Range: 5.1925. Min Range: -5.1925

Max Act: 5.0675. Min Act: -0.1700

Data Index: 1349087 (C4 (Web Text))

Max Activating Token Index: 571

Text #10

Max Range: 5.1925. Min Range: -5.1925

Max Act: 5.0675. Min Act: -0.1700

Data Index: 810279 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 5.1925. Min Range: -5.1925

Max Act: 5.0675. Min Act: -0.1700

Data Index: 1097273 (C4 (Web Text))

Max Activating Token Index: 714

Text #12

Max Range: 5.1925. Min Range: -5.1925

Max Act: 5.0675. Min Act: -0.1700

Data Index: 1087366 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 5.1925. Min Range: -5.1925

Max Act: 5.0675. Min Act: -0.1700

Data Index: 951572 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 5.1925. Min Range: -5.1925

Max Act: 5.0363. Min Act: -0.1700

Data Index: 1237828 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 5.1925. Min Range: -5.1925

Max Act: 5.0675. Min Act: -0.1700

Data Index: 173760 (C4 (Web Text))

Max Activating Token Index: 157

Text #16

Max Range: 5.1925. Min Range: -5.1925

Max Act: 5.0675. Min Act: -0.1700

Data Index: 833916 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 5.1925. Min Range: -5.1925

Max Act: 5.0363. Min Act: -0.1700

Data Index: 699513 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 5.1925. Min Range: -5.1925

Max Act: 5.0363. Min Act: -0.1700

Data Index: 560954 (C4 (Web Text))

Max Activating Token Index: 953

Text #19

Max Range: 5.1925. Min Range: -5.1925

Max Act: 5.0363. Min Act: -0.1700

Data Index: 810997 (C4 (Web Text))

Max Activating Token Index: 851