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

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

Neuron 1024 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: 3.4251. Min Range: -3.4251

Max Act: 3.4251. Min Act: -0.1700

Data Index: 1141335 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 3.4251. Min Range: -3.4251

Max Act: 3.3623. Min Act: -0.1700

Data Index: 1100568 (C4 (Web Text))

Max Activating Token Index: 619

Text #2

Max Range: 3.4251. Min Range: -3.4251

Max Act: 3.3780. Min Act: -0.1700

Data Index: 422522 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 3.4251. Min Range: -3.4251

Max Act: 3.3309. Min Act: -0.1700

Data Index: 1061608 (C4 (Web Text))

Max Activating Token Index: 988

Text #4

Max Range: 3.4251. Min Range: -3.4251

Max Act: 3.2995. Min Act: -0.1700

Data Index: 376395 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 3.4251. Min Range: -3.4251

Max Act: 3.2681. Min Act: -0.1700

Data Index: 451268 (C4 (Web Text))

Max Activating Token Index: 973

Text #6

Max Range: 3.4251. Min Range: -3.4251

Max Act: 3.2838. Min Act: -0.1700

Data Index: 838904 (C4 (Web Text))

Max Activating Token Index: 604

Text #7

Max Range: 3.4251. Min Range: -3.4251

Max Act: 3.2838. Min Act: -0.1700

Data Index: 1085058 (C4 (Web Text))

Max Activating Token Index: 817

Text #8

Max Range: 3.4251. Min Range: -3.4251

Max Act: 3.2838. Min Act: -0.1700

Data Index: 456594 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 3.4251. Min Range: -3.4251

Max Act: 3.2367. Min Act: -0.1700

Data Index: 658165 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 3.4251. Min Range: -3.4251

Max Act: 3.2681. Min Act: -0.1700

Data Index: 1211726 (C4 (Web Text))

Max Activating Token Index: 608

Text #11

Max Range: 3.4251. Min Range: -3.4251

Max Act: 3.2681. Min Act: -0.1700

Data Index: 1153847 (C4 (Web Text))

Max Activating Token Index: 920

Text #12

Max Range: 3.4251. Min Range: -3.4251

Max Act: 3.2209. Min Act: -0.1700

Data Index: 360308 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 3.4251. Min Range: -3.4251

Max Act: 3.2681. Min Act: -0.1700

Data Index: 972796 (C4 (Web Text))

Max Activating Token Index: 665

Text #14

Max Range: 3.4251. Min Range: -3.4251

Max Act: 3.2681. Min Act: -0.1700

Data Index: 592670 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 3.4251. Min Range: -3.4251

Max Act: 3.2367. Min Act: -0.1700

Data Index: 162499 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 3.4251. Min Range: -3.4251

Max Act: 3.3152. Min Act: -0.1700

Data Index: 818929 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 3.4251. Min Range: -3.4251

Max Act: 3.2524. Min Act: -0.1700

Data Index: 126278 (C4 (Web Text))

Max Activating Token Index: 740

Text #18

Max Range: 3.4251. Min Range: -3.4251

Max Act: 3.2209. Min Act: -0.1700

Data Index: 1153994 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 3.4251. Min Range: -3.4251

Max Act: 3.2524. Min Act: -0.1700

Data Index: 791619 (C4 (Web Text))

Max Activating Token Index: 810