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

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

Neuron 45 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: 5.5701. Min Range: -5.5701

Max Act: 5.5701. Min Act: -0.1700

Data Index: 559308 (C4 (Web Text))

Max Activating Token Index: 973

Text #1

Max Range: 5.5701. Min Range: -5.5701

Max Act: 5.3514. Min Act: -0.1700

Data Index: 956427 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 5.5701. Min Range: -5.5701

Max Act: 5.2889. Min Act: -0.1700

Data Index: 817232 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 5.5701. Min Range: -5.5701

Max Act: 5.3514. Min Act: -0.1700

Data Index: 519860 (C4 (Web Text))

Max Activating Token Index: 800

Text #4

Max Range: 5.5701. Min Range: -5.5701

Max Act: 5.2576. Min Act: -0.1700

Data Index: 1257985 (C4 (Web Text))

Max Activating Token Index: 709

Text #5

Max Range: 5.5701. Min Range: -5.5701

Max Act: 5.2576. Min Act: -0.1700

Data Index: 66006 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 5.5701. Min Range: -5.5701

Max Act: 5.2576. Min Act: -0.1700

Data Index: 962358 (C4 (Web Text))

Max Activating Token Index: 129

Text #7

Max Range: 5.5701. Min Range: -5.5701

Max Act: 5.2264. Min Act: -0.1700

Data Index: 846454 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 5.5701. Min Range: -5.5701

Max Act: 5.2576. Min Act: -0.1700

Data Index: 362779 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 5.5701. Min Range: -5.5701

Max Act: 5.2264. Min Act: -0.1700

Data Index: 783971 (C4 (Web Text))

Max Activating Token Index: 788

Text #10

Max Range: 5.5701. Min Range: -5.5701

Max Act: 5.2576. Min Act: -0.1700

Data Index: 157822 (C4 (Web Text))

Max Activating Token Index: 529

Text #11

Max Range: 5.5701. Min Range: -5.5701

Max Act: 5.1951. Min Act: -0.1700

Data Index: 773377 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 5.5701. Min Range: -5.5701

Max Act: 5.1951. Min Act: -0.1700

Data Index: 829856 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 5.5701. Min Range: -5.5701

Max Act: 5.1951. Min Act: -0.1700

Data Index: 621829 (C4 (Web Text))

Max Activating Token Index: 904

Text #14

Max Range: 5.5701. Min Range: -5.5701

Max Act: 5.1951. Min Act: -0.1700

Data Index: 121250 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 5.5701. Min Range: -5.5701

Max Act: 5.1326. Min Act: -0.1700

Data Index: 1205857 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 5.5701. Min Range: -5.5701

Max Act: 5.0701. Min Act: -0.1700

Data Index: 355907 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 5.5701. Min Range: -5.5701

Max Act: 5.1639. Min Act: -0.1700

Data Index: 975359 (C4 (Web Text))

Max Activating Token Index: 760

Text #18

Max Range: 5.5701. Min Range: -5.5701

Max Act: 5.1951. Min Act: -0.1700

Data Index: 301087 (C4 (Web Text))

Max Activating Token Index: 562

Text #19

Max Range: 5.5701. Min Range: -5.5701

Max Act: 5.1639. Min Act: -0.1700

Data Index: 319479 (C4 (Web Text))

Max Activating Token Index: 940