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

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

Neuron 790 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.4505. Min Range: -5.4505

Max Act: 5.4505. Min Act: -0.1700

Data Index: 858114 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 5.4505. Min Range: -5.4505

Max Act: 5.3567. Min Act: -0.1700

Data Index: 787643 (C4 (Web Text))

Max Activating Token Index: 291

Text #2

Max Range: 5.4505. Min Range: -5.4505

Max Act: 5.2317. Min Act: -0.1700

Data Index: 251798 (C4 (Web Text))

Max Activating Token Index: 674

Text #3

Max Range: 5.4505. Min Range: -5.4505

Max Act: 5.3255. Min Act: -0.1700

Data Index: 53762 (C4 (Web Text))

Max Activating Token Index: 589

Text #4

Max Range: 5.4505. Min Range: -5.4505

Max Act: 5.4505. Min Act: -0.1700

Data Index: 1011526 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 5.4505. Min Range: -5.4505

Max Act: 5.2005. Min Act: -0.1700

Data Index: 657015 (C4 (Web Text))

Max Activating Token Index: 865

Text #6

Max Range: 5.4505. Min Range: -5.4505

Max Act: 5.2317. Min Act: -0.1700

Data Index: 554770 (C4 (Web Text))

Max Activating Token Index: 762

Text #7

Max Range: 5.4505. Min Range: -5.4505

Max Act: 5.2317. Min Act: -0.1700

Data Index: 496237 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 5.4505. Min Range: -5.4505

Max Act: 5.2005. Min Act: -0.1700

Data Index: 1111441 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 5.4505. Min Range: -5.4505

Max Act: 5.2005. Min Act: -0.1700

Data Index: 645932 (C4 (Web Text))

Max Activating Token Index: 91

Text #10

Max Range: 5.4505. Min Range: -5.4505

Max Act: 5.2005. Min Act: -0.1700

Data Index: 925902 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 5.4505. Min Range: -5.4505

Max Act: 5.1067. Min Act: -0.1700

Data Index: 1476232 (Python Code)

Max Activating Token Index: 309

Text #12

Max Range: 5.4505. Min Range: -5.4505

Max Act: 5.1067. Min Act: -0.1700

Data Index: 1197986 (C4 (Web Text))

Max Activating Token Index: 587

Text #13

Max Range: 5.4505. Min Range: -5.4505

Max Act: 5.0755. Min Act: -0.1700

Data Index: 1109310 (C4 (Web Text))

Max Activating Token Index: 145

Text #14

Max Range: 5.4505. Min Range: -5.4505

Max Act: 5.0755. Min Act: -0.1700

Data Index: 312456 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 5.4505. Min Range: -5.4505

Max Act: 5.0130. Min Act: -0.1700

Data Index: 1268641 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 5.4505. Min Range: -5.4505

Max Act: 5.0755. Min Act: -0.1700

Data Index: 1305152 (C4 (Web Text))

Max Activating Token Index: 38

Text #17

Max Range: 5.4505. Min Range: -5.4505

Max Act: 5.0755. Min Act: -0.1700

Data Index: 894251 (C4 (Web Text))

Max Activating Token Index: 196

Text #18

Max Range: 5.4505. Min Range: -5.4505

Max Act: 4.9817. Min Act: -0.1700

Data Index: 791258 (C4 (Web Text))

Max Activating Token Index: 944

Text #19

Max Range: 5.4505. Min Range: -5.4505

Max Act: 5.0442. Min Act: -0.1700

Data Index: 574866 (C4 (Web Text))

Max Activating Token Index: 856