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

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

Neuron 1710 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: 5.1043. Min Range: -5.1043

Max Act: 5.1043. Min Act: -0.1700

Data Index: 750020 (C4 (Web Text))

Max Activating Token Index: 514

Text #1

Max Range: 5.1043. Min Range: -5.1043

Max Act: 5.1043. Min Act: -0.1700

Data Index: 876626 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 5.1043. Min Range: -5.1043

Max Act: 5.1043. Min Act: -0.1700

Data Index: 802895 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 5.1043. Min Range: -5.1043

Max Act: 5.1043. Min Act: -0.1700

Data Index: 419998 (C4 (Web Text))

Max Activating Token Index: 531

Text #4

Max Range: 5.1043. Min Range: -5.1043

Max Act: 5.0106. Min Act: -0.1700

Data Index: 118432 (C4 (Web Text))

Max Activating Token Index: 455

Text #5

Max Range: 5.1043. Min Range: -5.1043

Max Act: 5.0106. Min Act: -0.1700

Data Index: 386208 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 5.1043. Min Range: -5.1043

Max Act: 5.0731. Min Act: -0.1700

Data Index: 489032 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 5.1043. Min Range: -5.1043

Max Act: 4.9793. Min Act: -0.1700

Data Index: 806251 (C4 (Web Text))

Max Activating Token Index: 539

Text #8

Max Range: 5.1043. Min Range: -5.1043

Max Act: 4.9481. Min Act: -0.1700

Data Index: 1061198 (C4 (Web Text))

Max Activating Token Index: 877

Text #9

Max Range: 5.1043. Min Range: -5.1043

Max Act: 4.9481. Min Act: -0.1700

Data Index: 673170 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 5.1043. Min Range: -5.1043

Max Act: 4.9168. Min Act: -0.1700

Data Index: 697394 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 5.1043. Min Range: -5.1043

Max Act: 4.9793. Min Act: -0.1700

Data Index: 275111 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 5.1043. Min Range: -5.1043

Max Act: 4.9168. Min Act: -0.1700

Data Index: 796197 (C4 (Web Text))

Max Activating Token Index: 919

Text #13

Max Range: 5.1043. Min Range: -5.1043

Max Act: 4.9481. Min Act: -0.1700

Data Index: 777185 (C4 (Web Text))

Max Activating Token Index: 530

Text #14

Max Range: 5.1043. Min Range: -5.1043

Max Act: 4.8856. Min Act: -0.1700

Data Index: 843849 (C4 (Web Text))

Max Activating Token Index: 246

Text #15

Max Range: 5.1043. Min Range: -5.1043

Max Act: 4.8856. Min Act: -0.1700

Data Index: 1137675 (C4 (Web Text))

Max Activating Token Index: 808

Text #16

Max Range: 5.1043. Min Range: -5.1043

Max Act: 4.8543. Min Act: -0.1700

Data Index: 446003 (C4 (Web Text))

Max Activating Token Index: 820

Text #17

Max Range: 5.1043. Min Range: -5.1043

Max Act: 4.8543. Min Act: -0.1700

Data Index: 358466 (C4 (Web Text))

Max Activating Token Index: 492

Text #18

Max Range: 5.1043. Min Range: -5.1043

Max Act: 4.7918. Min Act: -0.1700

Data Index: 755751 (C4 (Web Text))

Max Activating Token Index: 628

Text #19

Max Range: 5.1043. Min Range: -5.1043

Max Act: 4.8543. Min Act: -0.1700

Data Index: 513779 (C4 (Web Text))

Max Activating Token Index: 740