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

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

Neuron 431 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: 4.3827. Min Range: -4.3827

Max Act: 4.3827. Min Act: -0.1700

Data Index: 362870 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 4.3827. Min Range: -4.3827

Max Act: 3.8512. Min Act: -0.1700

Data Index: 223244 (C4 (Web Text))

Max Activating Token Index: 952

Text #2

Max Range: 4.3827. Min Range: -4.3827

Max Act: 3.7887. Min Act: -0.1700

Data Index: 725126 (C4 (Web Text))

Max Activating Token Index: 343

Text #3

Max Range: 4.3827. Min Range: -4.3827

Max Act: 3.7887. Min Act: -0.1700

Data Index: 312242 (C4 (Web Text))

Max Activating Token Index: 731

Text #4

Max Range: 4.3827. Min Range: -4.3827

Max Act: 3.7574. Min Act: -0.1700

Data Index: 758179 (C4 (Web Text))

Max Activating Token Index: 582

Text #5

Max Range: 4.3827. Min Range: -4.3827

Max Act: 3.7887. Min Act: -0.1700

Data Index: 843458 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 4.3827. Min Range: -4.3827

Max Act: 3.6635. Min Act: -0.1700

Data Index: 120223 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 4.3827. Min Range: -4.3827

Max Act: 3.7261. Min Act: -0.1700

Data Index: 637128 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 4.3827. Min Range: -4.3827

Max Act: 3.7261. Min Act: -0.1700

Data Index: 321977 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 4.3827. Min Range: -4.3827

Max Act: 3.6948. Min Act: -0.1700

Data Index: 355279 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 4.3827. Min Range: -4.3827

Max Act: 3.6635. Min Act: -0.1700

Data Index: 293161 (C4 (Web Text))

Max Activating Token Index: 97

Text #11

Max Range: 4.3827. Min Range: -4.3827

Max Act: 3.7261. Min Act: -0.1700

Data Index: 267311 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 4.3827. Min Range: -4.3827

Max Act: 3.6948. Min Act: -0.1700

Data Index: 926702 (C4 (Web Text))

Max Activating Token Index: 255

Text #13

Max Range: 4.3827. Min Range: -4.3827

Max Act: 3.6948. Min Act: -0.1700

Data Index: 1224097 (C4 (Web Text))

Max Activating Token Index: 780

Text #14

Max Range: 4.3827. Min Range: -4.3827

Max Act: 3.6948. Min Act: -0.1700

Data Index: 1322203 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 4.3827. Min Range: -4.3827

Max Act: 3.6948. Min Act: -0.1700

Data Index: 336732 (C4 (Web Text))

Max Activating Token Index: 806

Text #16

Max Range: 4.3827. Min Range: -4.3827

Max Act: 3.6635. Min Act: -0.1700

Data Index: 88628 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 4.3827. Min Range: -4.3827

Max Act: 3.6948. Min Act: -0.1700

Data Index: 245858 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 4.3827. Min Range: -4.3827

Max Act: 3.6635. Min Act: -0.1700

Data Index: 236604 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 4.3827. Min Range: -4.3827

Max Act: 3.6322. Min Act: -0.1700

Data Index: 774738 (C4 (Web Text))

Max Activating Token Index: 1023