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

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

Neuron 167 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: 5.4196. Min Range: -5.4196

Max Act: 5.4196. Min Act: -0.1700

Data Index: 853561 (C4 (Web Text))

Max Activating Token Index: 635

Text #1

Max Range: 5.4196. Min Range: -5.4196

Max Act: 5.3571. Min Act: -0.1700

Data Index: 1136870 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 5.4196. Min Range: -5.4196

Max Act: 5.3571. Min Act: -0.1700

Data Index: 443609 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 5.4196. Min Range: -5.4196

Max Act: 5.1696. Min Act: -0.1700

Data Index: 910911 (C4 (Web Text))

Max Activating Token Index: 513

Text #4

Max Range: 5.4196. Min Range: -5.4196

Max Act: 5.1696. Min Act: -0.1700

Data Index: 718839 (C4 (Web Text))

Max Activating Token Index: 574

Text #5

Max Range: 5.4196. Min Range: -5.4196

Max Act: 5.1696. Min Act: -0.1700

Data Index: 299932 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 5.4196. Min Range: -5.4196

Max Act: 5.0758. Min Act: -0.1700

Data Index: 20642 (C4 (Web Text))

Max Activating Token Index: 697

Text #7

Max Range: 5.4196. Min Range: -5.4196

Max Act: 5.1071. Min Act: -0.1700

Data Index: 1358140 (C4 (Web Text))

Max Activating Token Index: 437

Text #8

Max Range: 5.4196. Min Range: -5.4196

Max Act: 4.9821. Min Act: -0.1700

Data Index: 1203504 (C4 (Web Text))

Max Activating Token Index: 405

Text #9

Max Range: 5.4196. Min Range: -5.4196

Max Act: 4.9821. Min Act: -0.1700

Data Index: 424317 (C4 (Web Text))

Max Activating Token Index: 243

Text #10

Max Range: 5.4196. Min Range: -5.4196

Max Act: 4.9508. Min Act: -0.1700

Data Index: 1231074 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 5.4196. Min Range: -5.4196

Max Act: 5.0133. Min Act: -0.1700

Data Index: 1302997 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 5.4196. Min Range: -5.4196

Max Act: 4.9508. Min Act: -0.1700

Data Index: 1204395 (C4 (Web Text))

Max Activating Token Index: 694

Text #13

Max Range: 5.4196. Min Range: -5.4196

Max Act: 4.9821. Min Act: -0.1700

Data Index: 755432 (C4 (Web Text))

Max Activating Token Index: 679

Text #14

Max Range: 5.4196. Min Range: -5.4196

Max Act: 4.9821. Min Act: -0.1700

Data Index: 426237 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 5.4196. Min Range: -5.4196

Max Act: 4.8571. Min Act: -0.1700

Data Index: 1012560 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 5.4196. Min Range: -5.4196

Max Act: 4.8883. Min Act: -0.1700

Data Index: 1057351 (C4 (Web Text))

Max Activating Token Index: 880

Text #17

Max Range: 5.4196. Min Range: -5.4196

Max Act: 4.8571. Min Act: -0.1700

Data Index: 544378 (C4 (Web Text))

Max Activating Token Index: 255

Text #18

Max Range: 5.4196. Min Range: -5.4196

Max Act: 4.8258. Min Act: -0.1700

Data Index: 77531 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 5.4196. Min Range: -5.4196

Max Act: 4.7946. Min Act: -0.1700

Data Index: 1136968 (C4 (Web Text))

Max Activating Token Index: 810