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

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

Neuron 32 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: 5.9785. Min Range: -5.9785

Max Act: 5.9785. Min Act: -0.1700

Data Index: 494835 (C4 (Web Text))

Max Activating Token Index: 295

Text #1

Max Range: 5.9785. Min Range: -5.9785

Max Act: 5.9160. Min Act: -0.1700

Data Index: 1239063 (C4 (Web Text))

Max Activating Token Index: 593

Text #2

Max Range: 5.9785. Min Range: -5.9785

Max Act: 5.9785. Min Act: -0.1700

Data Index: 281199 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 5.9785. Min Range: -5.9785

Max Act: 5.8847. Min Act: -0.1700

Data Index: 604015 (C4 (Web Text))

Max Activating Token Index: 394

Text #4

Max Range: 5.9785. Min Range: -5.9785

Max Act: 5.8535. Min Act: -0.1700

Data Index: 29429 (C4 (Web Text))

Max Activating Token Index: 133

Text #5

Max Range: 5.9785. Min Range: -5.9785

Max Act: 5.7285. Min Act: -0.1700

Data Index: 812718 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 5.9785. Min Range: -5.9785

Max Act: 5.8222. Min Act: -0.1700

Data Index: 132445 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 5.9785. Min Range: -5.9785

Max Act: 5.7910. Min Act: -0.1700

Data Index: 248324 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 5.9785. Min Range: -5.9785

Max Act: 5.6972. Min Act: -0.1700

Data Index: 777666 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 5.9785. Min Range: -5.9785

Max Act: 5.7597. Min Act: -0.1700

Data Index: 394286 (C4 (Web Text))

Max Activating Token Index: 227

Text #10

Max Range: 5.9785. Min Range: -5.9785

Max Act: 5.6972. Min Act: -0.1700

Data Index: 1056292 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 5.9785. Min Range: -5.9785

Max Act: 5.6972. Min Act: -0.1700

Data Index: 899134 (C4 (Web Text))

Max Activating Token Index: 258

Text #12

Max Range: 5.9785. Min Range: -5.9785

Max Act: 5.7910. Min Act: -0.1700

Data Index: 1346794 (C4 (Web Text))

Max Activating Token Index: 819

Text #13

Max Range: 5.9785. Min Range: -5.9785

Max Act: 5.6660. Min Act: -0.1700

Data Index: 879210 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 5.9785. Min Range: -5.9785

Max Act: 5.6660. Min Act: -0.1700

Data Index: 513641 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 5.9785. Min Range: -5.9785

Max Act: 5.6660. Min Act: -0.1700

Data Index: 341791 (C4 (Web Text))

Max Activating Token Index: 246

Text #16

Max Range: 5.9785. Min Range: -5.9785

Max Act: 5.6972. Min Act: -0.1700

Data Index: 722688 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 5.9785. Min Range: -5.9785

Max Act: 5.6972. Min Act: -0.1700

Data Index: 80842 (C4 (Web Text))

Max Activating Token Index: 569

Text #18

Max Range: 5.9785. Min Range: -5.9785

Max Act: 5.7597. Min Act: -0.1700

Data Index: 314174 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 5.9785. Min Range: -5.9785

Max Act: 5.6660. Min Act: -0.1700

Data Index: 729741 (C4 (Web Text))

Max Activating Token Index: 307