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

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

Neuron 1324 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: 3.7354. Min Range: -3.7354

Max Act: 3.7354. Min Act: -0.1700

Data Index: 321070 (C4 (Web Text))

Max Activating Token Index: 684

Text #1

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.7354. Min Act: -0.1700

Data Index: 1310491 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.7354. Min Act: -0.1700

Data Index: 608499 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.6415. Min Act: -0.1700

Data Index: 1123572 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.6102. Min Act: -0.1700

Data Index: 179554 (C4 (Web Text))

Max Activating Token Index: 857

Text #5

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.6102. Min Act: -0.1700

Data Index: 1040630 (C4 (Web Text))

Max Activating Token Index: 73

Text #6

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.6102. Min Act: -0.1700

Data Index: 1290237 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.5789. Min Act: -0.1700

Data Index: 1188101 (C4 (Web Text))

Max Activating Token Index: 530

Text #8

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.5789. Min Act: -0.1700

Data Index: 143210 (C4 (Web Text))

Max Activating Token Index: 224

Text #9

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.5789. Min Act: -0.1700

Data Index: 1262127 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.5476. Min Act: -0.1700

Data Index: 627941 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.5162. Min Act: -0.1700

Data Index: 1094946 (C4 (Web Text))

Max Activating Token Index: 1012

Text #12

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.5789. Min Act: -0.1700

Data Index: 95628 (C4 (Web Text))

Max Activating Token Index: 414

Text #13

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.5476. Min Act: -0.1700

Data Index: 165141 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.5162. Min Act: -0.1700

Data Index: 692621 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.4849. Min Act: -0.1700

Data Index: 251855 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.4536. Min Act: -0.1700

Data Index: 144978 (C4 (Web Text))

Max Activating Token Index: 673

Text #17

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.4849. Min Act: -0.1700

Data Index: 1291937 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.4849. Min Act: -0.1700

Data Index: 1261307 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 3.7354. Min Range: -3.7354

Max Act: 3.4222. Min Act: -0.1700

Data Index: 563266 (C4 (Web Text))

Max Activating Token Index: 58