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

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

Neuron 736 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.8670. Min Act: -0.1700

Data Index: 1282195 (C4 (Web Text))

Max Activating Token Index: 572

Text #1

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.8358. Min Act: -0.1700

Data Index: 717103 (C4 (Web Text))

Max Activating Token Index: 328

Text #2

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.7889. Min Act: -0.1700

Data Index: 159512 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.8358. Min Act: -0.1700

Data Index: 83997 (C4 (Web Text))

Max Activating Token Index: 118

Text #4

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.7889. Min Act: -0.1700

Data Index: 1237885 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.7576. Min Act: -0.1700

Data Index: 129725 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.7419. Min Act: -0.1700

Data Index: 284613 (C4 (Web Text))

Max Activating Token Index: 18

Text #7

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.7732. Min Act: -0.1700

Data Index: 833724 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.7732. Min Act: -0.1700

Data Index: 494276 (C4 (Web Text))

Max Activating Token Index: 650

Text #9

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.7263. Min Act: -0.1700

Data Index: 320212 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.6793. Min Act: -0.1700

Data Index: 898210 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.6793. Min Act: -0.1700

Data Index: 778927 (C4 (Web Text))

Max Activating Token Index: 477

Text #12

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.6637. Min Act: -0.1700

Data Index: 17664 (C4 (Web Text))

Max Activating Token Index: 682

Text #13

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.6793. Min Act: -0.1700

Data Index: 275500 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.7263. Min Act: -0.1700

Data Index: 612294 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.6950. Min Act: -0.1700

Data Index: 913445 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.7106. Min Act: -0.1700

Data Index: 343379 (C4 (Web Text))

Max Activating Token Index: 509

Text #17

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.6793. Min Act: -0.1700

Data Index: 236827 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.7106. Min Act: -0.1700

Data Index: 99502 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 3.8670. Min Range: -3.8670

Max Act: 3.6950. Min Act: -0.1700

Data Index: 1204106 (C4 (Web Text))

Max Activating Token Index: 751