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

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

Neuron 1203 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: 4.1323. Min Range: -4.1323

Max Act: 4.1323. Min Act: -0.1700

Data Index: 440927 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.9447. Min Act: -0.1700

Data Index: 31294 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.9134. Min Act: -0.1700

Data Index: 727812 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.8196. Min Act: -0.1700

Data Index: 1222405 (C4 (Web Text))

Max Activating Token Index: 543

Text #4

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.8196. Min Act: -0.1700

Data Index: 810864 (C4 (Web Text))

Max Activating Token Index: 373

Text #5

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.8196. Min Act: -0.1700

Data Index: 1260338 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.8196. Min Act: -0.1700

Data Index: 860349 (C4 (Web Text))

Max Activating Token Index: 576

Text #7

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.7883. Min Act: -0.1700

Data Index: 1250158 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.7883. Min Act: -0.1700

Data Index: 1270640 (C4 (Web Text))

Max Activating Token Index: 538

Text #9

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.7883. Min Act: -0.1700

Data Index: 594944 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.7883. Min Act: -0.1700

Data Index: 1073846 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.7257. Min Act: -0.1700

Data Index: 1277245 (C4 (Web Text))

Max Activating Token Index: 373

Text #12

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.7570. Min Act: -0.1700

Data Index: 752108 (C4 (Web Text))

Max Activating Token Index: 468

Text #13

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.7570. Min Act: -0.1700

Data Index: 293722 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.7570. Min Act: -0.1700

Data Index: 643403 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.7257. Min Act: -0.1700

Data Index: 318674 (C4 (Web Text))

Max Activating Token Index: 569

Text #16

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.7570. Min Act: -0.1700

Data Index: 1091319 (C4 (Web Text))

Max Activating Token Index: 809

Text #17

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.7257. Min Act: -0.1700

Data Index: 712044 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.6944. Min Act: -0.1700

Data Index: 181512 (C4 (Web Text))

Max Activating Token Index: 839

Text #19

Max Range: 4.1323. Min Range: -4.1323

Max Act: 3.6944. Min Act: -0.1700

Data Index: 374291 (C4 (Web Text))

Max Activating Token Index: 846