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

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

Neuron 502 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.3819. Min Act: -0.1700

Data Index: 60395 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.3035. Min Act: -0.1700

Data Index: 725460 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.3192. Min Act: -0.1700

Data Index: 593073 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.2878. Min Act: -0.1700

Data Index: 714357 (C4 (Web Text))

Max Activating Token Index: 746

Text #4

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.3035. Min Act: -0.1700

Data Index: 422701 (C4 (Web Text))

Max Activating Token Index: 410

Text #5

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.2720. Min Act: -0.1700

Data Index: 1204810 (C4 (Web Text))

Max Activating Token Index: 675

Text #6

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.2878. Min Act: -0.1700

Data Index: 25859 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.3035. Min Act: -0.1700

Data Index: 191616 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.3035. Min Act: -0.1700

Data Index: 440856 (C4 (Web Text))

Max Activating Token Index: 189

Text #9

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.2720. Min Act: -0.1700

Data Index: 899023 (C4 (Web Text))

Max Activating Token Index: 826

Text #10

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.2878. Min Act: -0.1700

Data Index: 653850 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.2878. Min Act: -0.1700

Data Index: 34897 (C4 (Web Text))

Max Activating Token Index: 66

Text #12

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.2878. Min Act: -0.1700

Data Index: 1256300 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.2878. Min Act: -0.1700

Data Index: 355965 (C4 (Web Text))

Max Activating Token Index: 168

Text #14

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.2878. Min Act: -0.1700

Data Index: 614563 (C4 (Web Text))

Max Activating Token Index: 972

Text #15

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.2878. Min Act: -0.1700

Data Index: 217392 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.2878. Min Act: -0.1700

Data Index: 540669 (C4 (Web Text))

Max Activating Token Index: 18

Text #17

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.2720. Min Act: -0.1700

Data Index: 110549 (C4 (Web Text))

Max Activating Token Index: 696

Text #18

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.2563. Min Act: -0.1700

Data Index: 928320 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 3.3819. Min Range: -3.3819

Max Act: 3.2563. Min Act: -0.1700

Data Index: 1074140 (C4 (Web Text))

Max Activating Token Index: 425