Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1943 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 5.2044. Min Range: -5.2044

Max Act: 5.2044. Min Act: -0.1700

Data Index: 1154104 (C4 (Web Text))

Max Activating Token Index: 802

Text #1

Max Range: 5.2044. Min Range: -5.2044

Max Act: 5.1106. Min Act: -0.1700

Data Index: 788948 (C4 (Web Text))

Max Activating Token Index: 966

Text #2

Max Range: 5.2044. Min Range: -5.2044

Max Act: 5.0169. Min Act: -0.1700

Data Index: 854656 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 5.2044. Min Range: -5.2044

Max Act: 5.0481. Min Act: -0.1700

Data Index: 775576 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 5.2044. Min Range: -5.2044

Max Act: 4.9856. Min Act: -0.1700

Data Index: 1257877 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 5.2044. Min Range: -5.2044

Max Act: 4.9856. Min Act: -0.1700

Data Index: 804313 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 5.2044. Min Range: -5.2044

Max Act: 4.9544. Min Act: -0.1700

Data Index: 877119 (C4 (Web Text))

Max Activating Token Index: 903

Text #7

Max Range: 5.2044. Min Range: -5.2044

Max Act: 4.9231. Min Act: -0.1700

Data Index: 1244457 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 5.2044. Min Range: -5.2044

Max Act: 4.9231. Min Act: -0.1700

Data Index: 1048980 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 5.2044. Min Range: -5.2044

Max Act: 4.9231. Min Act: -0.1700

Data Index: 774784 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 5.2044. Min Range: -5.2044

Max Act: 4.9231. Min Act: -0.1700

Data Index: 1172851 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 5.2044. Min Range: -5.2044

Max Act: 4.8606. Min Act: -0.1700

Data Index: 1075773 (C4 (Web Text))

Max Activating Token Index: 145

Text #12

Max Range: 5.2044. Min Range: -5.2044

Max Act: 4.8919. Min Act: -0.1700

Data Index: 555176 (C4 (Web Text))

Max Activating Token Index: 34

Text #13

Max Range: 5.2044. Min Range: -5.2044

Max Act: 4.8606. Min Act: -0.1700

Data Index: 868937 (C4 (Web Text))

Max Activating Token Index: 795

Text #14

Max Range: 5.2044. Min Range: -5.2044

Max Act: 4.8606. Min Act: -0.1700

Data Index: 799618 (C4 (Web Text))

Max Activating Token Index: 908

Text #15

Max Range: 5.2044. Min Range: -5.2044

Max Act: 4.8606. Min Act: -0.1700

Data Index: 679872 (C4 (Web Text))

Max Activating Token Index: 108

Text #16

Max Range: 5.2044. Min Range: -5.2044

Max Act: 4.8606. Min Act: -0.1700

Data Index: 238349 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 5.2044. Min Range: -5.2044

Max Act: 4.8606. Min Act: -0.1700

Data Index: 556400 (C4 (Web Text))

Max Activating Token Index: 623

Text #18

Max Range: 5.2044. Min Range: -5.2044

Max Act: 4.8919. Min Act: -0.1700

Data Index: 655051 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 5.2044. Min Range: -5.2044

Max Act: 4.8294. Min Act: -0.1700

Data Index: 967965 (C4 (Web Text))

Max Activating Token Index: 300