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

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

Neuron 834 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: 5.6891. Min Range: -5.6891

Max Act: 5.6891. Min Act: -0.1700

Data Index: 817957 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 5.6891. Min Range: -5.6891

Max Act: 5.5954. Min Act: -0.1700

Data Index: 1351333 (C4 (Web Text))

Max Activating Token Index: 714

Text #2

Max Range: 5.6891. Min Range: -5.6891

Max Act: 5.5016. Min Act: -0.1700

Data Index: 950404 (C4 (Web Text))

Max Activating Token Index: 621

Text #3

Max Range: 5.6891. Min Range: -5.6891

Max Act: 5.4704. Min Act: -0.1700

Data Index: 869380 (C4 (Web Text))

Max Activating Token Index: 588

Text #4

Max Range: 5.6891. Min Range: -5.6891

Max Act: 5.4391. Min Act: -0.1700

Data Index: 1092021 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 5.6891. Min Range: -5.6891

Max Act: 5.4704. Min Act: -0.1700

Data Index: 492677 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 5.6891. Min Range: -5.6891

Max Act: 5.4704. Min Act: -0.1700

Data Index: 1027650 (C4 (Web Text))

Max Activating Token Index: 721

Text #7

Max Range: 5.6891. Min Range: -5.6891

Max Act: 5.5016. Min Act: -0.1700

Data Index: 544625 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 5.6891. Min Range: -5.6891

Max Act: 5.5016. Min Act: -0.1700

Data Index: 1280362 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 5.6891. Min Range: -5.6891

Max Act: 5.4704. Min Act: -0.1700

Data Index: 1122428 (C4 (Web Text))

Max Activating Token Index: 368

Text #10

Max Range: 5.6891. Min Range: -5.6891

Max Act: 5.5329. Min Act: -0.1700

Data Index: 254319 (C4 (Web Text))

Max Activating Token Index: 534

Text #11

Max Range: 5.6891. Min Range: -5.6891

Max Act: 5.4079. Min Act: -0.1700

Data Index: 234397 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 5.6891. Min Range: -5.6891

Max Act: 5.4079. Min Act: -0.1700

Data Index: 910588 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 5.6891. Min Range: -5.6891

Max Act: 5.4079. Min Act: -0.1700

Data Index: 617868 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 5.6891. Min Range: -5.6891

Max Act: 5.4079. Min Act: -0.1700

Data Index: 409373 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 5.6891. Min Range: -5.6891

Max Act: 5.4391. Min Act: -0.1700

Data Index: 1086487 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 5.6891. Min Range: -5.6891

Max Act: 5.3454. Min Act: -0.1700

Data Index: 1225015 (C4 (Web Text))

Max Activating Token Index: 872

Text #17

Max Range: 5.6891. Min Range: -5.6891

Max Act: 5.3766. Min Act: -0.1700

Data Index: 1200847 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 5.6891. Min Range: -5.6891

Max Act: 5.4079. Min Act: -0.1700

Data Index: 1282412 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 5.6891. Min Range: -5.6891

Max Act: 5.3766. Min Act: -0.1700

Data Index: 574842 (C4 (Web Text))

Max Activating Token Index: 805