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

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

Neuron 1969 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4386. Min Range: -3.4386

Max Act: 3.4386. Min Act: -0.1700

Data Index: 848832 (C4 (Web Text))

Max Activating Token Index: 67

Text #1

Max Range: 3.4386. Min Range: -3.4386

Max Act: 3.3758. Min Act: -0.1700

Data Index: 1209862 (C4 (Web Text))

Max Activating Token Index: 364

Text #2

Max Range: 3.4386. Min Range: -3.4386

Max Act: 3.3758. Min Act: -0.1700

Data Index: 718310 (C4 (Web Text))

Max Activating Token Index: 677

Text #3

Max Range: 3.4386. Min Range: -3.4386

Max Act: 3.2816. Min Act: -0.1700

Data Index: 195933 (C4 (Web Text))

Max Activating Token Index: 737

Text #4

Max Range: 3.4386. Min Range: -3.4386

Max Act: 3.2345. Min Act: -0.1700

Data Index: 920906 (C4 (Web Text))

Max Activating Token Index: 969

Text #5

Max Range: 3.4386. Min Range: -3.4386

Max Act: 3.1873. Min Act: -0.1700

Data Index: 106582 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 3.4386. Min Range: -3.4386

Max Act: 3.2030. Min Act: -0.1700

Data Index: 837632 (C4 (Web Text))

Max Activating Token Index: 915

Text #7

Max Range: 3.4386. Min Range: -3.4386

Max Act: 3.1873. Min Act: -0.1700

Data Index: 71249 (C4 (Web Text))

Max Activating Token Index: 616

Text #8

Max Range: 3.4386. Min Range: -3.4386

Max Act: 3.1715. Min Act: -0.1700

Data Index: 1255363 (C4 (Web Text))

Max Activating Token Index: 936

Text #9

Max Range: 3.4386. Min Range: -3.4386

Max Act: 3.1715. Min Act: -0.1700

Data Index: 1158958 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 3.4386. Min Range: -3.4386

Max Act: 3.1558. Min Act: -0.1700

Data Index: 438880 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 3.4386. Min Range: -3.4386

Max Act: 3.1558. Min Act: -0.1700

Data Index: 56708 (C4 (Web Text))

Max Activating Token Index: 316

Text #12

Max Range: 3.4386. Min Range: -3.4386

Max Act: 3.1243. Min Act: -0.1700

Data Index: 1125696 (C4 (Web Text))

Max Activating Token Index: 363

Text #13

Max Range: 3.4386. Min Range: -3.4386

Max Act: 3.1243. Min Act: -0.1700

Data Index: 64717 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 3.4386. Min Range: -3.4386

Max Act: 3.1243. Min Act: -0.1700

Data Index: 157454 (C4 (Web Text))

Max Activating Token Index: 570

Text #15

Max Range: 3.4386. Min Range: -3.4386

Max Act: 3.1243. Min Act: -0.1700

Data Index: 872953 (C4 (Web Text))

Max Activating Token Index: 485

Text #16

Max Range: 3.4386. Min Range: -3.4386

Max Act: 3.0928. Min Act: -0.1700

Data Index: 766768 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 3.4386. Min Range: -3.4386

Max Act: 3.0454. Min Act: -0.1700

Data Index: 657387 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 3.4386. Min Range: -3.4386

Max Act: 3.0770. Min Act: -0.1700

Data Index: 650237 (C4 (Web Text))

Max Activating Token Index: 445

Text #19

Max Range: 3.4386. Min Range: -3.4386

Max Act: 3.0454. Min Act: -0.1700

Data Index: 947769 (C4 (Web Text))

Max Activating Token Index: 655