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

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

Neuron 1907 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6441. Min Range: -5.6441

Max Act: 5.6441. Min Act: -0.1700

Data Index: 342661 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 5.6441. Min Range: -5.6441

Max Act: 5.5816. Min Act: -0.1700

Data Index: 412828 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 5.6441. Min Range: -5.6441

Max Act: 5.5503. Min Act: -0.1700

Data Index: 207765 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 5.6441. Min Range: -5.6441

Max Act: 5.5503. Min Act: -0.1700

Data Index: 373788 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 5.6441. Min Range: -5.6441

Max Act: 5.5816. Min Act: -0.1700

Data Index: 1011748 (C4 (Web Text))

Max Activating Token Index: 928

Text #5

Max Range: 5.6441. Min Range: -5.6441

Max Act: 5.4878. Min Act: -0.1700

Data Index: 708134 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 5.6441. Min Range: -5.6441

Max Act: 5.4566. Min Act: -0.1700

Data Index: 691982 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 5.6441. Min Range: -5.6441

Max Act: 5.4253. Min Act: -0.1700

Data Index: 208229 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 5.6441. Min Range: -5.6441

Max Act: 5.3941. Min Act: -0.1700

Data Index: 24900 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 5.6441. Min Range: -5.6441

Max Act: 5.4253. Min Act: -0.1700

Data Index: 633462 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 5.6441. Min Range: -5.6441

Max Act: 5.4253. Min Act: -0.1700

Data Index: 1205691 (C4 (Web Text))

Max Activating Token Index: 817

Text #11

Max Range: 5.6441. Min Range: -5.6441

Max Act: 5.3941. Min Act: -0.1700

Data Index: 766018 (C4 (Web Text))

Max Activating Token Index: 518

Text #12

Max Range: 5.6441. Min Range: -5.6441

Max Act: 5.3316. Min Act: -0.1700

Data Index: 200328 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 5.6441. Min Range: -5.6441

Max Act: 5.3628. Min Act: -0.1700

Data Index: 413895 (C4 (Web Text))

Max Activating Token Index: 911

Text #14

Max Range: 5.6441. Min Range: -5.6441

Max Act: 5.3628. Min Act: -0.1700

Data Index: 351630 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 5.6441. Min Range: -5.6441

Max Act: 5.3316. Min Act: -0.1700

Data Index: 1059992 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 5.6441. Min Range: -5.6441

Max Act: 5.3628. Min Act: -0.1700

Data Index: 74396 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 5.6441. Min Range: -5.6441

Max Act: 5.3316. Min Act: -0.1700

Data Index: 522715 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 5.6441. Min Range: -5.6441

Max Act: 5.3316. Min Act: -0.1700

Data Index: 979330 (C4 (Web Text))

Max Activating Token Index: 395

Text #19

Max Range: 5.6441. Min Range: -5.6441

Max Act: 5.3316. Min Act: -0.1700

Data Index: 776751 (C4 (Web Text))

Max Activating Token Index: 904