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

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

Neuron 1187 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: 5.1024. Min Range: -5.1024

Max Act: 5.1024. Min Act: -0.1700

Data Index: 1271302 (C4 (Web Text))

Max Activating Token Index: 506

Text #1

Max Range: 5.1024. Min Range: -5.1024

Max Act: 4.9149. Min Act: -0.1700

Data Index: 27362 (C4 (Web Text))

Max Activating Token Index: 582

Text #2

Max Range: 5.1024. Min Range: -5.1024

Max Act: 4.9305. Min Act: -0.1700

Data Index: 980544 (C4 (Web Text))

Max Activating Token Index: 452

Text #3

Max Range: 5.1024. Min Range: -5.1024

Max Act: 4.8368. Min Act: -0.1700

Data Index: 149409 (C4 (Web Text))

Max Activating Token Index: 699

Text #4

Max Range: 5.1024. Min Range: -5.1024

Max Act: 4.8211. Min Act: -0.1700

Data Index: 466713 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 5.1024. Min Range: -5.1024

Max Act: 4.9149. Min Act: -0.1700

Data Index: 21567 (C4 (Web Text))

Max Activating Token Index: 762

Text #6

Max Range: 5.1024. Min Range: -5.1024

Max Act: 4.8836. Min Act: -0.1700

Data Index: 610069 (C4 (Web Text))

Max Activating Token Index: 419

Text #7

Max Range: 5.1024. Min Range: -5.1024

Max Act: 4.8524. Min Act: -0.1700

Data Index: 893108 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 5.1024. Min Range: -5.1024

Max Act: 4.7743. Min Act: -0.1700

Data Index: 295733 (C4 (Web Text))

Max Activating Token Index: 719

Text #9

Max Range: 5.1024. Min Range: -5.1024

Max Act: 4.7899. Min Act: -0.1700

Data Index: 758762 (C4 (Web Text))

Max Activating Token Index: 448

Text #10

Max Range: 5.1024. Min Range: -5.1024

Max Act: 4.7899. Min Act: -0.1700

Data Index: 1326346 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 5.1024. Min Range: -5.1024

Max Act: 4.7743. Min Act: -0.1700

Data Index: 1057126 (C4 (Web Text))

Max Activating Token Index: 805

Text #12

Max Range: 5.1024. Min Range: -5.1024

Max Act: 4.8524. Min Act: -0.1700

Data Index: 1191300 (C4 (Web Text))

Max Activating Token Index: 754

Text #13

Max Range: 5.1024. Min Range: -5.1024

Max Act: 4.8211. Min Act: -0.1700

Data Index: 406238 (C4 (Web Text))

Max Activating Token Index: 130

Text #14

Max Range: 5.1024. Min Range: -5.1024

Max Act: 4.7743. Min Act: -0.1700

Data Index: 763325 (C4 (Web Text))

Max Activating Token Index: 354

Text #15

Max Range: 5.1024. Min Range: -5.1024

Max Act: 4.8055. Min Act: -0.1700

Data Index: 147134 (C4 (Web Text))

Max Activating Token Index: 430

Text #16

Max Range: 5.1024. Min Range: -5.1024

Max Act: 4.7899. Min Act: -0.1700

Data Index: 12895 (C4 (Web Text))

Max Activating Token Index: 665

Text #17

Max Range: 5.1024. Min Range: -5.1024

Max Act: 4.8055. Min Act: -0.1700

Data Index: 1469 (C4 (Web Text))

Max Activating Token Index: 732

Text #18

Max Range: 5.1024. Min Range: -5.1024

Max Act: 4.7743. Min Act: -0.1700

Data Index: 78059 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 5.1024. Min Range: -5.1024

Max Act: 4.7743. Min Act: -0.1700

Data Index: 928689 (C4 (Web Text))

Max Activating Token Index: 503