Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1920 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 8.7826. Min Range: -8.7826

Max Act: 8.7826. Min Act: -0.1700

Data Index: 1325927 (C4 (Web Text))

Max Activating Token Index: 365

Text #1

Max Range: 8.7826. Min Range: -8.7826

Max Act: 8.6264. Min Act: -0.1699

Data Index: 759614 (C4 (Web Text))

Max Activating Token Index: 487

Text #2

Max Range: 8.7826. Min Range: -8.7826

Max Act: 8.6889. Min Act: -0.1700

Data Index: 777319 (C4 (Web Text))

Max Activating Token Index: 787

Text #3

Max Range: 8.7826. Min Range: -8.7826

Max Act: 8.6576. Min Act: -0.1700

Data Index: 169688 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 8.7826. Min Range: -8.7826

Max Act: 8.6576. Min Act: -0.1700

Data Index: 994995 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 8.7826. Min Range: -8.7826

Max Act: 8.6264. Min Act: -0.1700

Data Index: 223547 (C4 (Web Text))

Max Activating Token Index: 918

Text #6

Max Range: 8.7826. Min Range: -8.7826

Max Act: 8.6576. Min Act: -0.1699

Data Index: 317780 (C4 (Web Text))

Max Activating Token Index: 276

Text #7

Max Range: 8.7826. Min Range: -8.7826

Max Act: 8.6264. Min Act: -0.1670

Data Index: 884188 (C4 (Web Text))

Max Activating Token Index: 189

Text #8

Max Range: 8.7826. Min Range: -8.7826

Max Act: 8.6264. Min Act: -0.1699

Data Index: 543252 (C4 (Web Text))

Max Activating Token Index: 206

Text #9

Max Range: 8.7826. Min Range: -8.7826

Max Act: 8.5639. Min Act: -0.1700

Data Index: 958596 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 8.7826. Min Range: -8.7826

Max Act: 8.5951. Min Act: -0.1682

Data Index: 1021270 (C4 (Web Text))

Max Activating Token Index: 275

Text #11

Max Range: 8.7826. Min Range: -8.7826

Max Act: 8.6576. Min Act: -0.1700

Data Index: 283728 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 8.7826. Min Range: -8.7826

Max Act: 8.6264. Min Act: -0.1700

Data Index: 287507 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 8.7826. Min Range: -8.7826

Max Act: 8.5639. Min Act: -0.1699

Data Index: 369717 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 8.7826. Min Range: -8.7826

Max Act: 8.5639. Min Act: -0.1699

Data Index: 1301012 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 8.7826. Min Range: -8.7826

Max Act: 8.4389. Min Act: -0.1700

Data Index: 1199259 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 8.7826. Min Range: -8.7826

Max Act: 8.5014. Min Act: -0.1700

Data Index: 899817 (C4 (Web Text))

Max Activating Token Index: 171

Text #17

Max Range: 8.7826. Min Range: -8.7826

Max Act: 8.5326. Min Act: -0.1699

Data Index: 921257 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 8.7826. Min Range: -8.7826

Max Act: 8.5014. Min Act: -0.1700

Data Index: 1063354 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 8.7826. Min Range: -8.7826

Max Act: 8.5014. Min Act: -0.1699

Data Index: 579921 (C4 (Web Text))

Max Activating Token Index: 847