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

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

Neuron 1723 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: 4.1600. Min Range: -4.1600

Max Act: 4.1600. Min Act: -0.1700

Data Index: 214970 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 4.1600. Min Range: -4.1600

Max Act: 4.1287. Min Act: -0.1700

Data Index: 881675 (C4 (Web Text))

Max Activating Token Index: 617

Text #2

Max Range: 4.1600. Min Range: -4.1600

Max Act: 4.0662. Min Act: -0.1700

Data Index: 564676 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 4.1600. Min Range: -4.1600

Max Act: 4.0349. Min Act: -0.1700

Data Index: 1217624 (C4 (Web Text))

Max Activating Token Index: 29

Text #4

Max Range: 4.1600. Min Range: -4.1600

Max Act: 4.0349. Min Act: -0.1700

Data Index: 115236 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 4.1600. Min Range: -4.1600

Max Act: 4.0036. Min Act: -0.1700

Data Index: 1275885 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 4.1600. Min Range: -4.1600

Max Act: 4.0974. Min Act: -0.1700

Data Index: 191805 (C4 (Web Text))

Max Activating Token Index: 401

Text #7

Max Range: 4.1600. Min Range: -4.1600

Max Act: 3.9098. Min Act: -0.1700

Data Index: 1296630 (C4 (Web Text))

Max Activating Token Index: 682

Text #8

Max Range: 4.1600. Min Range: -4.1600

Max Act: 3.9411. Min Act: -0.1700

Data Index: 1042528 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 4.1600. Min Range: -4.1600

Max Act: 3.9411. Min Act: -0.1700

Data Index: 1093290 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 4.1600. Min Range: -4.1600

Max Act: 3.9411. Min Act: -0.1700

Data Index: 378931 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 4.1600. Min Range: -4.1600

Max Act: 3.9724. Min Act: -0.1700

Data Index: 930252 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 4.1600. Min Range: -4.1600

Max Act: 3.8473. Min Act: -0.1700

Data Index: 933418 (C4 (Web Text))

Max Activating Token Index: 589

Text #13

Max Range: 4.1600. Min Range: -4.1600

Max Act: 3.8786. Min Act: -0.1700

Data Index: 447521 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 4.1600. Min Range: -4.1600

Max Act: 3.8160. Min Act: -0.1700

Data Index: 517939 (C4 (Web Text))

Max Activating Token Index: 483

Text #15

Max Range: 4.1600. Min Range: -4.1600

Max Act: 3.8160. Min Act: -0.1700

Data Index: 1224413 (C4 (Web Text))

Max Activating Token Index: 678

Text #16

Max Range: 4.1600. Min Range: -4.1600

Max Act: 3.8786. Min Act: -0.1700

Data Index: 155492 (C4 (Web Text))

Max Activating Token Index: 796

Text #17

Max Range: 4.1600. Min Range: -4.1600

Max Act: 3.8160. Min Act: -0.1700

Data Index: 1004683 (C4 (Web Text))

Max Activating Token Index: 463

Text #18

Max Range: 4.1600. Min Range: -4.1600

Max Act: 3.8473. Min Act: -0.1700

Data Index: 774542 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 4.1600. Min Range: -4.1600

Max Act: 3.8160. Min Act: -0.1700

Data Index: 1114498 (C4 (Web Text))

Max Activating Token Index: 951