Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1976 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.7546. Min Act: -0.1700

Data Index: 967662 (C4 (Web Text))

Max Activating Token Index: 638

Text #1

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.5355. Min Act: -0.1700

Data Index: 566530 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.5668. Min Act: -0.1700

Data Index: 560657 (C4 (Web Text))

Max Activating Token Index: 812

Text #3

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.5355. Min Act: -0.1700

Data Index: 252959 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.5042. Min Act: -0.1700

Data Index: 451416 (C4 (Web Text))

Max Activating Token Index: 811

Text #5

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.4415. Min Act: -0.1700

Data Index: 723538 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.3944. Min Act: -0.1700

Data Index: 791919 (C4 (Web Text))

Max Activating Token Index: 428

Text #7

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.4258. Min Act: -0.1700

Data Index: 884877 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.3474. Min Act: -0.1700

Data Index: 576728 (C4 (Web Text))

Max Activating Token Index: 778

Text #9

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.3787. Min Act: -0.1700

Data Index: 1174064 (C4 (Web Text))

Max Activating Token Index: 289

Text #10

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.3474. Min Act: -0.1700

Data Index: 1293589 (C4 (Web Text))

Max Activating Token Index: 914

Text #11

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.2688. Min Act: -0.1700

Data Index: 181875 (C4 (Web Text))

Max Activating Token Index: 918

Text #12

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.2688. Min Act: -0.1700

Data Index: 296391 (C4 (Web Text))

Max Activating Token Index: 790

Text #13

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.3317. Min Act: -0.1700

Data Index: 479174 (C4 (Web Text))

Max Activating Token Index: 727

Text #14

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.3002. Min Act: -0.1700

Data Index: 557871 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.2531. Min Act: -0.1700

Data Index: 436960 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.2374. Min Act: -0.1700

Data Index: 732408 (C4 (Web Text))

Max Activating Token Index: 846

Text #17

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.2059. Min Act: -0.1700

Data Index: 152077 (C4 (Web Text))

Max Activating Token Index: 990

Text #18

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.2531. Min Act: -0.1700

Data Index: 193462 (C4 (Web Text))

Max Activating Token Index: 1002

Text #19

Max Range: 3.7546. Min Range: -3.7546

Max Act: 3.2531. Min Act: -0.1700

Data Index: 348444 (C4 (Web Text))

Max Activating Token Index: 960