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

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

Neuron 1409 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: 5.5061. Min Range: -5.5061

Max Act: 5.5061. Min Act: -0.1700

Data Index: 218771 (C4 (Web Text))

Max Activating Token Index: 1011

Text #1

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.4123. Min Act: -0.1700

Data Index: 275186 (C4 (Web Text))

Max Activating Token Index: 36

Text #2

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.3186. Min Act: -0.1700

Data Index: 1412548 (Python Code)

Max Activating Token Index: 1021

Text #3

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.2561. Min Act: -0.1700

Data Index: 239401 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.2561. Min Act: -0.1700

Data Index: 550771 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.2248. Min Act: -0.1700

Data Index: 225152 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.2873. Min Act: -0.1700

Data Index: 1536867 (Python Code)

Max Activating Token Index: 596

Text #7

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.1936. Min Act: -0.1700

Data Index: 550745 (C4 (Web Text))

Max Activating Token Index: 630

Text #8

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.2873. Min Act: -0.1700

Data Index: 791619 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.2248. Min Act: -0.1700

Data Index: 676045 (C4 (Web Text))

Max Activating Token Index: 639

Text #10

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.2873. Min Act: -0.1700

Data Index: 1215279 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.1936. Min Act: -0.1700

Data Index: 580780 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.1311. Min Act: -0.1700

Data Index: 1622363 (Python Code)

Max Activating Token Index: 633

Text #13

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.1936. Min Act: -0.1700

Data Index: 1581800 (Python Code)

Max Activating Token Index: 868

Text #14

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.1936. Min Act: -0.1700

Data Index: 1416174 (Python Code)

Max Activating Token Index: 673

Text #15

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.2248. Min Act: -0.1700

Data Index: 1514830 (Python Code)

Max Activating Token Index: 561

Text #16

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.2248. Min Act: -0.1700

Data Index: 148002 (C4 (Web Text))

Max Activating Token Index: 525

Text #17

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.1936. Min Act: -0.1700

Data Index: 1044943 (C4 (Web Text))

Max Activating Token Index: 835

Text #18

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.1936. Min Act: -0.1700

Data Index: 276664 (C4 (Web Text))

Max Activating Token Index: 160

Text #19

Max Range: 5.5061. Min Range: -5.5061

Max Act: 5.1936. Min Act: -0.1700

Data Index: 1092939 (C4 (Web Text))

Max Activating Token Index: 843