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

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

Neuron 815 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: 3.5141. Min Range: -3.5141

Max Act: 3.5141. Min Act: -0.1700

Data Index: 502793 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 3.5141. Min Range: -3.5141

Max Act: 3.4828. Min Act: -0.1700

Data Index: 1170961 (C4 (Web Text))

Max Activating Token Index: 202

Text #2

Max Range: 3.5141. Min Range: -3.5141

Max Act: 3.4514. Min Act: -0.1700

Data Index: 435388 (C4 (Web Text))

Max Activating Token Index: 428

Text #3

Max Range: 3.5141. Min Range: -3.5141

Max Act: 3.4671. Min Act: -0.1700

Data Index: 47149 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 3.5141. Min Range: -3.5141

Max Act: 3.4201. Min Act: -0.1700

Data Index: 513353 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 3.5141. Min Range: -3.5141

Max Act: 3.4358. Min Act: -0.1700

Data Index: 414755 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 3.5141. Min Range: -3.5141

Max Act: 3.4201. Min Act: -0.1700

Data Index: 1227720 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 3.5141. Min Range: -3.5141

Max Act: 3.4358. Min Act: -0.1700

Data Index: 266268 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 3.5141. Min Range: -3.5141

Max Act: 3.4044. Min Act: -0.1700

Data Index: 447893 (C4 (Web Text))

Max Activating Token Index: 404

Text #9

Max Range: 3.5141. Min Range: -3.5141

Max Act: 3.4201. Min Act: -0.1700

Data Index: 894066 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 3.5141. Min Range: -3.5141

Max Act: 3.3887. Min Act: -0.1700

Data Index: 48660 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 3.5141. Min Range: -3.5141

Max Act: 3.4201. Min Act: -0.1700

Data Index: 941915 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 3.5141. Min Range: -3.5141

Max Act: 3.3887. Min Act: -0.1700

Data Index: 41424 (C4 (Web Text))

Max Activating Token Index: 649

Text #13

Max Range: 3.5141. Min Range: -3.5141

Max Act: 3.4201. Min Act: -0.1700

Data Index: 559739 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 3.5141. Min Range: -3.5141

Max Act: 3.3887. Min Act: -0.1700

Data Index: 426032 (C4 (Web Text))

Max Activating Token Index: 784

Text #15

Max Range: 3.5141. Min Range: -3.5141

Max Act: 3.3730. Min Act: -0.1700

Data Index: 578425 (C4 (Web Text))

Max Activating Token Index: 586

Text #16

Max Range: 3.5141. Min Range: -3.5141

Max Act: 3.3416. Min Act: -0.1700

Data Index: 209651 (C4 (Web Text))

Max Activating Token Index: 420

Text #17

Max Range: 3.5141. Min Range: -3.5141

Max Act: 3.3730. Min Act: -0.1700

Data Index: 1320240 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 3.5141. Min Range: -3.5141

Max Act: 3.4514. Min Act: -0.1700

Data Index: 228876 (C4 (Web Text))

Max Activating Token Index: 387

Text #19

Max Range: 3.5141. Min Range: -3.5141

Max Act: 3.4201. Min Act: -0.1700

Data Index: 764165 (C4 (Web Text))

Max Activating Token Index: 337