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

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

Neuron 593 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3883. Min Range: -3.3883

Max Act: 3.3883. Min Act: -0.1700

Data Index: 705241 (C4 (Web Text))

Max Activating Token Index: 699

Text #1

Max Range: 3.3883. Min Range: -3.3883

Max Act: 3.3726. Min Act: -0.1700

Data Index: 636677 (C4 (Web Text))

Max Activating Token Index: 846

Text #2

Max Range: 3.3883. Min Range: -3.3883

Max Act: 3.3255. Min Act: -0.1700

Data Index: 1035352 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 3.3883. Min Range: -3.3883

Max Act: 3.3412. Min Act: -0.1700

Data Index: 477545 (C4 (Web Text))

Max Activating Token Index: 607

Text #4

Max Range: 3.3883. Min Range: -3.3883

Max Act: 3.3255. Min Act: -0.1700

Data Index: 322862 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 3.3883. Min Range: -3.3883

Max Act: 3.2941. Min Act: -0.1700

Data Index: 267673 (C4 (Web Text))

Max Activating Token Index: 690

Text #6

Max Range: 3.3883. Min Range: -3.3883

Max Act: 3.3255. Min Act: -0.1700

Data Index: 962656 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 3.3883. Min Range: -3.3883

Max Act: 3.3098. Min Act: -0.1700

Data Index: 588211 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 3.3883. Min Range: -3.3883

Max Act: 3.2784. Min Act: -0.1700

Data Index: 320725 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 3.3883. Min Range: -3.3883

Max Act: 3.2313. Min Act: -0.1700

Data Index: 486460 (C4 (Web Text))

Max Activating Token Index: 908

Text #10

Max Range: 3.3883. Min Range: -3.3883

Max Act: 3.2155. Min Act: -0.1700

Data Index: 1252485 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 3.3883. Min Range: -3.3883

Max Act: 3.2155. Min Act: -0.1700

Data Index: 119511 (C4 (Web Text))

Max Activating Token Index: 702

Text #12

Max Range: 3.3883. Min Range: -3.3883

Max Act: 3.2155. Min Act: -0.1700

Data Index: 776699 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 3.3883. Min Range: -3.3883

Max Act: 3.1841. Min Act: -0.1700

Data Index: 469462 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 3.3883. Min Range: -3.3883

Max Act: 3.1526. Min Act: -0.1700

Data Index: 1245980 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 3.3883. Min Range: -3.3883

Max Act: 3.1841. Min Act: -0.1700

Data Index: 921181 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 3.3883. Min Range: -3.3883

Max Act: 3.1841. Min Act: -0.1700

Data Index: 500861 (C4 (Web Text))

Max Activating Token Index: 228

Text #17

Max Range: 3.3883. Min Range: -3.3883

Max Act: 3.1841. Min Act: -0.1700

Data Index: 522313 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 3.3883. Min Range: -3.3883

Max Act: 3.1683. Min Act: -0.1700

Data Index: 590411 (C4 (Web Text))

Max Activating Token Index: 798

Text #19

Max Range: 3.3883. Min Range: -3.3883

Max Act: 3.1683. Min Act: -0.1700

Data Index: 235636 (C4 (Web Text))

Max Activating Token Index: 657