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

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

Neuron 1440 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4833. Min Range: -3.4833

Max Act: 3.4833. Min Act: -0.1700

Data Index: 630566 (C4 (Web Text))

Max Activating Token Index: 357

Text #1

Max Range: 3.4833. Min Range: -3.4833

Max Act: 3.4519. Min Act: -0.1700

Data Index: 264210 (C4 (Web Text))

Max Activating Token Index: 784

Text #2

Max Range: 3.4833. Min Range: -3.4833

Max Act: 3.4049. Min Act: -0.1700

Data Index: 616328 (C4 (Web Text))

Max Activating Token Index: 300

Text #3

Max Range: 3.4833. Min Range: -3.4833

Max Act: 3.3735. Min Act: -0.1700

Data Index: 1116014 (C4 (Web Text))

Max Activating Token Index: 978

Text #4

Max Range: 3.4833. Min Range: -3.4833

Max Act: 3.2479. Min Act: -0.1700

Data Index: 556580 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 3.4833. Min Range: -3.4833

Max Act: 3.2479. Min Act: -0.1700

Data Index: 29941 (C4 (Web Text))

Max Activating Token Index: 638

Text #6

Max Range: 3.4833. Min Range: -3.4833

Max Act: 3.2322. Min Act: -0.1700

Data Index: 623161 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 3.4833. Min Range: -3.4833

Max Act: 3.2950. Min Act: -0.1700

Data Index: 1285250 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 3.4833. Min Range: -3.4833

Max Act: 3.2007. Min Act: -0.1700

Data Index: 1186244 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 3.4833. Min Range: -3.4833

Max Act: 3.2164. Min Act: -0.1700

Data Index: 109872 (C4 (Web Text))

Max Activating Token Index: 870

Text #10

Max Range: 3.4833. Min Range: -3.4833

Max Act: 3.2007. Min Act: -0.1700

Data Index: 322477 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 3.4833. Min Range: -3.4833

Max Act: 3.2164. Min Act: -0.1700

Data Index: 415159 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 3.4833. Min Range: -3.4833

Max Act: 3.2007. Min Act: -0.1700

Data Index: 660347 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 3.4833. Min Range: -3.4833

Max Act: 3.2007. Min Act: -0.1700

Data Index: 778671 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 3.4833. Min Range: -3.4833

Max Act: 3.1692. Min Act: -0.1700

Data Index: 888648 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 3.4833. Min Range: -3.4833

Max Act: 3.2007. Min Act: -0.1700

Data Index: 829345 (C4 (Web Text))

Max Activating Token Index: 975

Text #16

Max Range: 3.4833. Min Range: -3.4833

Max Act: 3.2164. Min Act: -0.1700

Data Index: 540142 (C4 (Web Text))

Max Activating Token Index: 118

Text #17

Max Range: 3.4833. Min Range: -3.4833

Max Act: 3.1692. Min Act: -0.1700

Data Index: 12108 (C4 (Web Text))

Max Activating Token Index: 722

Text #18

Max Range: 3.4833. Min Range: -3.4833

Max Act: 3.1692. Min Act: -0.1700

Data Index: 480287 (C4 (Web Text))

Max Activating Token Index: 545

Text #19

Max Range: 3.4833. Min Range: -3.4833

Max Act: 3.1850. Min Act: -0.1700

Data Index: 542031 (C4 (Web Text))

Max Activating Token Index: 303