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

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

Neuron 1164 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: 5.1073. Min Range: -5.1073

Max Act: 5.1073. Min Act: -0.1700

Data Index: 63339 (C4 (Web Text))

Max Activating Token Index: 455

Text #1

Max Range: 5.1073. Min Range: -5.1073

Max Act: 4.9198. Min Act: -0.1700

Data Index: 993587 (C4 (Web Text))

Max Activating Token Index: 779

Text #2

Max Range: 5.1073. Min Range: -5.1073

Max Act: 4.8885. Min Act: -0.1700

Data Index: 667352 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 5.1073. Min Range: -5.1073

Max Act: 4.8573. Min Act: -0.1700

Data Index: 720730 (C4 (Web Text))

Max Activating Token Index: 320

Text #4

Max Range: 5.1073. Min Range: -5.1073

Max Act: 4.7948. Min Act: -0.1700

Data Index: 1309184 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 5.1073. Min Range: -5.1073

Max Act: 4.7323. Min Act: -0.1700

Data Index: 1198589 (C4 (Web Text))

Max Activating Token Index: 295

Text #6

Max Range: 5.1073. Min Range: -5.1073

Max Act: 4.7010. Min Act: -0.1700

Data Index: 110312 (C4 (Web Text))

Max Activating Token Index: 439

Text #7

Max Range: 5.1073. Min Range: -5.1073

Max Act: 4.7323. Min Act: -0.1700

Data Index: 648651 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 5.1073. Min Range: -5.1073

Max Act: 4.7635. Min Act: -0.1700

Data Index: 813090 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 5.1073. Min Range: -5.1073

Max Act: 4.7010. Min Act: -0.1700

Data Index: 726229 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 5.1073. Min Range: -5.1073

Max Act: 4.6698. Min Act: -0.1700

Data Index: 347747 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 5.1073. Min Range: -5.1073

Max Act: 4.6385. Min Act: -0.1700

Data Index: 1087906 (C4 (Web Text))

Max Activating Token Index: 249

Text #12

Max Range: 5.1073. Min Range: -5.1073

Max Act: 4.6385. Min Act: -0.1700

Data Index: 894467 (C4 (Web Text))

Max Activating Token Index: 550

Text #13

Max Range: 5.1073. Min Range: -5.1073

Max Act: 4.6698. Min Act: -0.1700

Data Index: 74207 (C4 (Web Text))

Max Activating Token Index: 489

Text #14

Max Range: 5.1073. Min Range: -5.1073

Max Act: 4.6385. Min Act: -0.1700

Data Index: 1298978 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 5.1073. Min Range: -5.1073

Max Act: 4.6385. Min Act: -0.1700

Data Index: 1307862 (C4 (Web Text))

Max Activating Token Index: 227

Text #16

Max Range: 5.1073. Min Range: -5.1073

Max Act: 4.6698. Min Act: -0.1700

Data Index: 1190915 (C4 (Web Text))

Max Activating Token Index: 399

Text #17

Max Range: 5.1073. Min Range: -5.1073

Max Act: 4.5760. Min Act: -0.1700

Data Index: 11334 (C4 (Web Text))

Max Activating Token Index: 273

Text #18

Max Range: 5.1073. Min Range: -5.1073

Max Act: 4.5760. Min Act: -0.1700

Data Index: 208805 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 5.1073. Min Range: -5.1073

Max Act: 4.6073. Min Act: -0.1700

Data Index: 908355 (C4 (Web Text))

Max Activating Token Index: 437