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

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

Neuron 324 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: 5.6453. Min Range: -5.6453

Max Act: 5.6141. Min Act: -0.1700

Data Index: 730233 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 5.6453. Min Range: -5.6453

Max Act: 5.6453. Min Act: -0.1700

Data Index: 109419 (C4 (Web Text))

Max Activating Token Index: 794

Text #2

Max Range: 5.6453. Min Range: -5.6453

Max Act: 5.6141. Min Act: -0.1700

Data Index: 1258966 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 5.6453. Min Range: -5.6453

Max Act: 5.6141. Min Act: -0.1700

Data Index: 816604 (C4 (Web Text))

Max Activating Token Index: 964

Text #4

Max Range: 5.6453. Min Range: -5.6453

Max Act: 5.5828. Min Act: -0.1700

Data Index: 907611 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 5.6453. Min Range: -5.6453

Max Act: 5.5828. Min Act: -0.1700

Data Index: 744207 (C4 (Web Text))

Max Activating Token Index: 570

Text #6

Max Range: 5.6453. Min Range: -5.6453

Max Act: 5.5203. Min Act: -0.1700

Data Index: 658882 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 5.6453. Min Range: -5.6453

Max Act: 5.5203. Min Act: -0.1700

Data Index: 676286 (C4 (Web Text))

Max Activating Token Index: 440

Text #8

Max Range: 5.6453. Min Range: -5.6453

Max Act: 5.4578. Min Act: -0.1700

Data Index: 93514 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 5.6453. Min Range: -5.6453

Max Act: 5.4891. Min Act: -0.1700

Data Index: 287942 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 5.6453. Min Range: -5.6453

Max Act: 5.4891. Min Act: -0.1700

Data Index: 535133 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 5.6453. Min Range: -5.6453

Max Act: 5.4891. Min Act: -0.1700

Data Index: 713945 (C4 (Web Text))

Max Activating Token Index: 957

Text #12

Max Range: 5.6453. Min Range: -5.6453

Max Act: 5.4891. Min Act: -0.1700

Data Index: 1142032 (C4 (Web Text))

Max Activating Token Index: 315

Text #13

Max Range: 5.6453. Min Range: -5.6453

Max Act: 5.4891. Min Act: -0.1700

Data Index: 544072 (C4 (Web Text))

Max Activating Token Index: 947

Text #14

Max Range: 5.6453. Min Range: -5.6453

Max Act: 5.5203. Min Act: -0.1700

Data Index: 231570 (C4 (Web Text))

Max Activating Token Index: 677

Text #15

Max Range: 5.6453. Min Range: -5.6453

Max Act: 5.5203. Min Act: -0.1700

Data Index: 1119550 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 5.6453. Min Range: -5.6453

Max Act: 5.4578. Min Act: -0.1700

Data Index: 430434 (C4 (Web Text))

Max Activating Token Index: 439

Text #17

Max Range: 5.6453. Min Range: -5.6453

Max Act: 5.4266. Min Act: -0.1700

Data Index: 180387 (C4 (Web Text))

Max Activating Token Index: 280

Text #18

Max Range: 5.6453. Min Range: -5.6453

Max Act: 5.4578. Min Act: -0.1700

Data Index: 267013 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 5.6453. Min Range: -5.6453

Max Act: 5.4266. Min Act: -0.1700

Data Index: 1069743 (C4 (Web Text))

Max Activating Token Index: 762