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

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

Neuron 530 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.4602. Min Act: -0.1700

Data Index: 817906 (C4 (Web Text))

Max Activating Token Index: 608

Text #1

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.3664. Min Act: -0.1700

Data Index: 92302 (C4 (Web Text))

Max Activating Token Index: 863

Text #2

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.3977. Min Act: -0.1700

Data Index: 233872 (C4 (Web Text))

Max Activating Token Index: 220

Text #3

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.2727. Min Act: -0.1700

Data Index: 1341871 (C4 (Web Text))

Max Activating Token Index: 966

Text #4

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.2414. Min Act: -0.1699

Data Index: 1213473 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.2727. Min Act: -0.1700

Data Index: 608764 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.2414. Min Act: -0.1700

Data Index: 54592 (C4 (Web Text))

Max Activating Token Index: 526

Text #7

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.2727. Min Act: -0.1700

Data Index: 439517 (C4 (Web Text))

Max Activating Token Index: 313

Text #8

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.2102. Min Act: -0.1700

Data Index: 183040 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.1789. Min Act: -0.1700

Data Index: 439504 (C4 (Web Text))

Max Activating Token Index: 271

Text #10

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.2414. Min Act: -0.1700

Data Index: 641171 (C4 (Web Text))

Max Activating Token Index: 867

Text #11

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.2102. Min Act: -0.1700

Data Index: 823790 (C4 (Web Text))

Max Activating Token Index: 813

Text #12

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.1477. Min Act: -0.1700

Data Index: 414918 (C4 (Web Text))

Max Activating Token Index: 674

Text #13

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.1477. Min Act: -0.1700

Data Index: 25685 (C4 (Web Text))

Max Activating Token Index: 895

Text #14

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.1477. Min Act: -0.1700

Data Index: 106103 (C4 (Web Text))

Max Activating Token Index: 813

Text #15

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.1789. Min Act: -0.1700

Data Index: 941944 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.2102. Min Act: -0.1700

Data Index: 482002 (C4 (Web Text))

Max Activating Token Index: 930

Text #17

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.1477. Min Act: -0.1700

Data Index: 1305727 (C4 (Web Text))

Max Activating Token Index: 515

Text #18

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.1789. Min Act: -0.1700

Data Index: 297401 (C4 (Web Text))

Max Activating Token Index: 962

Text #19

Max Range: 5.4602. Min Range: -5.4602

Max Act: 5.1164. Min Act: -0.1700

Data Index: 1015216 (C4 (Web Text))

Max Activating Token Index: 890