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

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

Neuron 233 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: 3.4563. Min Range: -3.4563

Max Act: 3.4406. Min Act: -0.1700

Data Index: 1013431 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 3.4563. Min Range: -3.4563

Max Act: 3.4563. Min Act: -0.1700

Data Index: 57849 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 3.4563. Min Range: -3.4563

Max Act: 3.4406. Min Act: -0.1700

Data Index: 1002339 (C4 (Web Text))

Max Activating Token Index: 545

Text #3

Max Range: 3.4563. Min Range: -3.4563

Max Act: 3.4406. Min Act: -0.1700

Data Index: 468796 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 3.4563. Min Range: -3.4563

Max Act: 3.4092. Min Act: -0.1700

Data Index: 15107 (C4 (Web Text))

Max Activating Token Index: 535

Text #5

Max Range: 3.4563. Min Range: -3.4563

Max Act: 3.3465. Min Act: -0.1700

Data Index: 719711 (C4 (Web Text))

Max Activating Token Index: 480

Text #6

Max Range: 3.4563. Min Range: -3.4563

Max Act: 3.4249. Min Act: -0.1700

Data Index: 644447 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 3.4563. Min Range: -3.4563

Max Act: 3.3935. Min Act: -0.1700

Data Index: 199675 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 3.4563. Min Range: -3.4563

Max Act: 3.3935. Min Act: -0.1700

Data Index: 585004 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 3.4563. Min Range: -3.4563

Max Act: 3.4092. Min Act: -0.1700

Data Index: 440458 (C4 (Web Text))

Max Activating Token Index: 299

Text #10

Max Range: 3.4563. Min Range: -3.4563

Max Act: 3.3778. Min Act: -0.1700

Data Index: 1035658 (C4 (Web Text))

Max Activating Token Index: 922

Text #11

Max Range: 3.4563. Min Range: -3.4563

Max Act: 3.3622. Min Act: -0.1700

Data Index: 991067 (C4 (Web Text))

Max Activating Token Index: 238

Text #12

Max Range: 3.4563. Min Range: -3.4563

Max Act: 3.3778. Min Act: -0.1700

Data Index: 667834 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 3.4563. Min Range: -3.4563

Max Act: 3.3465. Min Act: -0.1700

Data Index: 948505 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 3.4563. Min Range: -3.4563

Max Act: 3.3622. Min Act: -0.1700

Data Index: 912915 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 3.4563. Min Range: -3.4563

Max Act: 3.3622. Min Act: -0.1700

Data Index: 497239 (C4 (Web Text))

Max Activating Token Index: 436

Text #16

Max Range: 3.4563. Min Range: -3.4563

Max Act: 3.3465. Min Act: -0.1700

Data Index: 324886 (C4 (Web Text))

Max Activating Token Index: 691

Text #17

Max Range: 3.4563. Min Range: -3.4563

Max Act: 3.2837. Min Act: -0.1700

Data Index: 312797 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 3.4563. Min Range: -3.4563

Max Act: 3.3622. Min Act: -0.1700

Data Index: 158523 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 3.4563. Min Range: -3.4563

Max Act: 3.3308. Min Act: -0.1700

Data Index: 588748 (C4 (Web Text))

Max Activating Token Index: 36