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

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

Neuron 1780 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: 3.9550. Min Range: -3.9550

Max Act: 3.9550. Min Act: -0.1700

Data Index: 444988 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.9237. Min Act: -0.1700

Data Index: 1077659 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.8924. Min Act: -0.1700

Data Index: 884993 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.7673. Min Act: -0.1700

Data Index: 702537 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.8299. Min Act: -0.1700

Data Index: 405701 (C4 (Web Text))

Max Activating Token Index: 640

Text #5

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.7986. Min Act: -0.1700

Data Index: 666258 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.7986. Min Act: -0.1700

Data Index: 1083813 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.7986. Min Act: -0.1700

Data Index: 528974 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.7673. Min Act: -0.1700

Data Index: 72837 (C4 (Web Text))

Max Activating Token Index: 941

Text #9

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.7673. Min Act: -0.1700

Data Index: 366952 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.7673. Min Act: -0.1700

Data Index: 232319 (C4 (Web Text))

Max Activating Token Index: 686

Text #11

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.7360. Min Act: -0.1700

Data Index: 298233 (C4 (Web Text))

Max Activating Token Index: 433

Text #12

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.7673. Min Act: -0.1700

Data Index: 311426 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.7673. Min Act: -0.1700

Data Index: 425849 (C4 (Web Text))

Max Activating Token Index: 640

Text #14

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.7673. Min Act: -0.1700

Data Index: 668660 (C4 (Web Text))

Max Activating Token Index: 557

Text #15

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.7360. Min Act: -0.1700

Data Index: 79573 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.7047. Min Act: -0.1700

Data Index: 1065735 (C4 (Web Text))

Max Activating Token Index: 720

Text #17

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.7360. Min Act: -0.1700

Data Index: 721527 (C4 (Web Text))

Max Activating Token Index: 766

Text #18

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.6734. Min Act: -0.1700

Data Index: 322065 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 3.9550. Min Range: -3.9550

Max Act: 3.7360. Min Act: -0.1700

Data Index: 136451 (C4 (Web Text))

Max Activating Token Index: 549