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

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

Neuron 1897 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.0216. Min Range: -7.0216

Max Act: 7.0216. Min Act: -0.1700

Data Index: 1027767 (C4 (Web Text))

Max Activating Token Index: 414

Text #1

Max Range: 7.0216. Min Range: -7.0216

Max Act: 6.9278. Min Act: -0.1700

Data Index: 603748 (C4 (Web Text))

Max Activating Token Index: 954

Text #2

Max Range: 7.0216. Min Range: -7.0216

Max Act: 6.7091. Min Act: -0.1700

Data Index: 825938 (C4 (Web Text))

Max Activating Token Index: 947

Text #3

Max Range: 7.0216. Min Range: -7.0216

Max Act: 6.8653. Min Act: -0.1700

Data Index: 915572 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 7.0216. Min Range: -7.0216

Max Act: 6.7716. Min Act: -0.1700

Data Index: 221790 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 7.0216. Min Range: -7.0216

Max Act: 6.7716. Min Act: -0.1700

Data Index: 520251 (C4 (Web Text))

Max Activating Token Index: 383

Text #6

Max Range: 7.0216. Min Range: -7.0216

Max Act: 6.7403. Min Act: -0.1700

Data Index: 1013289 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 7.0216. Min Range: -7.0216

Max Act: 6.7091. Min Act: -0.1700

Data Index: 1315131 (C4 (Web Text))

Max Activating Token Index: 788

Text #8

Max Range: 7.0216. Min Range: -7.0216

Max Act: 6.6778. Min Act: -0.1700

Data Index: 739914 (C4 (Web Text))

Max Activating Token Index: 751

Text #9

Max Range: 7.0216. Min Range: -7.0216

Max Act: 6.7403. Min Act: -0.1700

Data Index: 818359 (C4 (Web Text))

Max Activating Token Index: 587

Text #10

Max Range: 7.0216. Min Range: -7.0216

Max Act: 6.6466. Min Act: -0.1700

Data Index: 757601 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 7.0216. Min Range: -7.0216

Max Act: 6.7091. Min Act: -0.1700

Data Index: 621876 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 7.0216. Min Range: -7.0216

Max Act: 6.6466. Min Act: -0.1700

Data Index: 1100576 (C4 (Web Text))

Max Activating Token Index: 1022

Text #13

Max Range: 7.0216. Min Range: -7.0216

Max Act: 6.6778. Min Act: -0.1700

Data Index: 220562 (C4 (Web Text))

Max Activating Token Index: 35

Text #14

Max Range: 7.0216. Min Range: -7.0216

Max Act: 6.6466. Min Act: -0.1700

Data Index: 258182 (C4 (Web Text))

Max Activating Token Index: 663

Text #15

Max Range: 7.0216. Min Range: -7.0216

Max Act: 6.6153. Min Act: -0.1700

Data Index: 951706 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 7.0216. Min Range: -7.0216

Max Act: 6.6153. Min Act: -0.1700

Data Index: 580649 (C4 (Web Text))

Max Activating Token Index: 795

Text #17

Max Range: 7.0216. Min Range: -7.0216

Max Act: 6.6466. Min Act: -0.1700

Data Index: 587802 (C4 (Web Text))

Max Activating Token Index: 501

Text #18

Max Range: 7.0216. Min Range: -7.0216

Max Act: 6.6778. Min Act: -0.1700

Data Index: 40284 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 7.0216. Min Range: -7.0216

Max Act: 6.4903. Min Act: -0.1700

Data Index: 561468 (C4 (Web Text))

Max Activating Token Index: 734