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

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

Neuron 1716 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: 3.9216. Min Range: -3.9216

Max Act: 3.9216. Min Act: -0.1700

Data Index: 13416 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.8747. Min Act: -0.1700

Data Index: 1034524 (C4 (Web Text))

Max Activating Token Index: 870

Text #2

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.8747. Min Act: -0.1700

Data Index: 852831 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.8278. Min Act: -0.1700

Data Index: 630102 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.8591. Min Act: -0.1700

Data Index: 1200898 (C4 (Web Text))

Max Activating Token Index: 649

Text #5

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.8278. Min Act: -0.1700

Data Index: 31080 (C4 (Web Text))

Max Activating Token Index: 577

Text #6

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.7965. Min Act: -0.1700

Data Index: 862690 (C4 (Web Text))

Max Activating Token Index: 884

Text #7

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.7809. Min Act: -0.1700

Data Index: 1314734 (C4 (Web Text))

Max Activating Token Index: 858

Text #8

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.8122. Min Act: -0.1700

Data Index: 1178792 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.7496. Min Act: -0.1700

Data Index: 712059 (C4 (Web Text))

Max Activating Token Index: 291

Text #10

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.7340. Min Act: -0.1700

Data Index: 1252861 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.7340. Min Act: -0.1700

Data Index: 570308 (C4 (Web Text))

Max Activating Token Index: 483

Text #12

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.7653. Min Act: -0.1700

Data Index: 1237682 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.7027. Min Act: -0.1700

Data Index: 1221113 (C4 (Web Text))

Max Activating Token Index: 980

Text #14

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.6870. Min Act: -0.1700

Data Index: 1141617 (C4 (Web Text))

Max Activating Token Index: 634

Text #15

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.7340. Min Act: -0.1700

Data Index: 199809 (C4 (Web Text))

Max Activating Token Index: 849

Text #16

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.7496. Min Act: -0.1700

Data Index: 941248 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.7340. Min Act: -0.1700

Data Index: 997014 (C4 (Web Text))

Max Activating Token Index: 271

Text #18

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.7496. Min Act: -0.1700

Data Index: 339899 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 3.9216. Min Range: -3.9216

Max Act: 3.7653. Min Act: -0.1700

Data Index: 1083626 (C4 (Web Text))

Max Activating Token Index: 901