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

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

Neuron 1890 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: 3.7090. Min Range: -3.7090

Max Act: 3.7090. Min Act: -0.1700

Data Index: 805854 (C4 (Web Text))

Max Activating Token Index: 666

Text #1

Max Range: 3.7090. Min Range: -3.7090

Max Act: 3.5837. Min Act: -0.1700

Data Index: 900802 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 3.7090. Min Range: -3.7090

Max Act: 3.5524. Min Act: -0.1700

Data Index: 795874 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 3.7090. Min Range: -3.7090

Max Act: 3.5524. Min Act: -0.1700

Data Index: 7536 (C4 (Web Text))

Max Activating Token Index: 426

Text #4

Max Range: 3.7090. Min Range: -3.7090

Max Act: 3.5524. Min Act: -0.1699

Data Index: 700387 (C4 (Web Text))

Max Activating Token Index: 1014

Text #5

Max Range: 3.7090. Min Range: -3.7090

Max Act: 3.5211. Min Act: -0.1700

Data Index: 882203 (C4 (Web Text))

Max Activating Token Index: 919

Text #6

Max Range: 3.7090. Min Range: -3.7090

Max Act: 3.5211. Min Act: -0.1700

Data Index: 138927 (C4 (Web Text))

Max Activating Token Index: 287

Text #7

Max Range: 3.7090. Min Range: -3.7090

Max Act: 3.5054. Min Act: -0.1700

Data Index: 411790 (C4 (Web Text))

Max Activating Token Index: 978

Text #8

Max Range: 3.7090. Min Range: -3.7090

Max Act: 3.5211. Min Act: -0.1700

Data Index: 249726 (C4 (Web Text))

Max Activating Token Index: 980

Text #9

Max Range: 3.7090. Min Range: -3.7090

Max Act: 3.4898. Min Act: -0.1700

Data Index: 198112 (C4 (Web Text))

Max Activating Token Index: 772

Text #10

Max Range: 3.7090. Min Range: -3.7090

Max Act: 3.5211. Min Act: -0.1700

Data Index: 814857 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 3.7090. Min Range: -3.7090

Max Act: 3.4271. Min Act: -0.1700

Data Index: 250439 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 3.7090. Min Range: -3.7090

Max Act: 3.5054. Min Act: -0.1700

Data Index: 771812 (C4 (Web Text))

Max Activating Token Index: 336

Text #13

Max Range: 3.7090. Min Range: -3.7090

Max Act: 3.4898. Min Act: -0.1700

Data Index: 1242695 (C4 (Web Text))

Max Activating Token Index: 381

Text #14

Max Range: 3.7090. Min Range: -3.7090

Max Act: 3.4584. Min Act: -0.1700

Data Index: 86426 (C4 (Web Text))

Max Activating Token Index: 566

Text #15

Max Range: 3.7090. Min Range: -3.7090

Max Act: 3.4271. Min Act: -0.1700

Data Index: 1032254 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 3.7090. Min Range: -3.7090

Max Act: 3.4271. Min Act: -0.1700

Data Index: 1268636 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 3.7090. Min Range: -3.7090

Max Act: 3.4584. Min Act: -0.1699

Data Index: 1213300 (C4 (Web Text))

Max Activating Token Index: 673

Text #18

Max Range: 3.7090. Min Range: -3.7090

Max Act: 3.4584. Min Act: -0.1700

Data Index: 264000 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 3.7090. Min Range: -3.7090

Max Act: 3.4584. Min Act: -0.1700

Data Index: 1151537 (C4 (Web Text))

Max Activating Token Index: 292