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

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

Neuron 547 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3739. Min Range: -5.3739

Max Act: 5.3739. Min Act: -0.1700

Data Index: 1338071 (C4 (Web Text))

Max Activating Token Index: 1017

Text #1

Max Range: 5.3739. Min Range: -5.3739

Max Act: 5.2801. Min Act: -0.1700

Data Index: 1304946 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 5.3739. Min Range: -5.3739

Max Act: 5.0926. Min Act: -0.1700

Data Index: 638742 (C4 (Web Text))

Max Activating Token Index: 943

Text #3

Max Range: 5.3739. Min Range: -5.3739

Max Act: 5.1551. Min Act: -0.1700

Data Index: 559228 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 5.3739. Min Range: -5.3739

Max Act: 5.0614. Min Act: -0.1700

Data Index: 1296566 (C4 (Web Text))

Max Activating Token Index: 680

Text #5

Max Range: 5.3739. Min Range: -5.3739

Max Act: 5.1239. Min Act: -0.1700

Data Index: 205441 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 5.3739. Min Range: -5.3739

Max Act: 5.0301. Min Act: -0.1700

Data Index: 786372 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 5.3739. Min Range: -5.3739

Max Act: 5.0614. Min Act: -0.1700

Data Index: 1039987 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 5.3739. Min Range: -5.3739

Max Act: 5.0614. Min Act: -0.1700

Data Index: 891913 (C4 (Web Text))

Max Activating Token Index: 108

Text #9

Max Range: 5.3739. Min Range: -5.3739

Max Act: 5.0301. Min Act: -0.1700

Data Index: 36149 (C4 (Web Text))

Max Activating Token Index: 27

Text #10

Max Range: 5.3739. Min Range: -5.3739

Max Act: 5.0301. Min Act: -0.1700

Data Index: 935101 (C4 (Web Text))

Max Activating Token Index: 95

Text #11

Max Range: 5.3739. Min Range: -5.3739

Max Act: 5.0614. Min Act: -0.1699

Data Index: 455822 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 5.3739. Min Range: -5.3739

Max Act: 4.9364. Min Act: -0.1700

Data Index: 572673 (C4 (Web Text))

Max Activating Token Index: 158

Text #13

Max Range: 5.3739. Min Range: -5.3739

Max Act: 4.9989. Min Act: -0.1700

Data Index: 802211 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 5.3739. Min Range: -5.3739

Max Act: 5.0301. Min Act: -0.1700

Data Index: 3050 (C4 (Web Text))

Max Activating Token Index: 782

Text #15

Max Range: 5.3739. Min Range: -5.3739

Max Act: 5.0301. Min Act: -0.1700

Data Index: 971566 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 5.3739. Min Range: -5.3739

Max Act: 4.9364. Min Act: -0.1700

Data Index: 243047 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 5.3739. Min Range: -5.3739

Max Act: 4.9364. Min Act: -0.1700

Data Index: 992904 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 5.3739. Min Range: -5.3739

Max Act: 4.8426. Min Act: -0.1700

Data Index: 459166 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 5.3739. Min Range: -5.3739

Max Act: 4.9364. Min Act: -0.1700

Data Index: 329483 (C4 (Web Text))

Max Activating Token Index: 929