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

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

Neuron 1520 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: 5.6703. Min Range: -5.6703

Max Act: 5.6390. Min Act: -0.1700

Data Index: 725629 (C4 (Web Text))

Max Activating Token Index: 634

Text #1

Max Range: 5.6703. Min Range: -5.6703

Max Act: 5.6703. Min Act: -0.1700

Data Index: 1275407 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 5.6703. Min Range: -5.6703

Max Act: 5.5765. Min Act: -0.1700

Data Index: 585362 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 5.6703. Min Range: -5.6703

Max Act: 5.5765. Min Act: -0.1700

Data Index: 1330137 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 5.6703. Min Range: -5.6703

Max Act: 5.5765. Min Act: -0.1700

Data Index: 634781 (C4 (Web Text))

Max Activating Token Index: 732

Text #5

Max Range: 5.6703. Min Range: -5.6703

Max Act: 5.5765. Min Act: -0.1700

Data Index: 1238771 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 5.6703. Min Range: -5.6703

Max Act: 5.6390. Min Act: -0.1700

Data Index: 49545 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 5.6703. Min Range: -5.6703

Max Act: 5.4515. Min Act: -0.1700

Data Index: 246834 (C4 (Web Text))

Max Activating Token Index: 770

Text #8

Max Range: 5.6703. Min Range: -5.6703

Max Act: 5.5765. Min Act: -0.1700

Data Index: 699939 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 5.6703. Min Range: -5.6703

Max Act: 5.4828. Min Act: -0.1700

Data Index: 473830 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 5.6703. Min Range: -5.6703

Max Act: 5.4828. Min Act: -0.1700

Data Index: 330640 (C4 (Web Text))

Max Activating Token Index: 760

Text #11

Max Range: 5.6703. Min Range: -5.6703

Max Act: 5.4203. Min Act: -0.1700

Data Index: 906865 (C4 (Web Text))

Max Activating Token Index: 562

Text #12

Max Range: 5.6703. Min Range: -5.6703

Max Act: 5.4828. Min Act: -0.1700

Data Index: 1234414 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 5.6703. Min Range: -5.6703

Max Act: 5.4828. Min Act: -0.1700

Data Index: 1118787 (C4 (Web Text))

Max Activating Token Index: 424

Text #14

Max Range: 5.6703. Min Range: -5.6703

Max Act: 5.4828. Min Act: -0.1700

Data Index: 1234651 (C4 (Web Text))

Max Activating Token Index: 178

Text #15

Max Range: 5.6703. Min Range: -5.6703

Max Act: 5.4828. Min Act: -0.1700

Data Index: 205628 (C4 (Web Text))

Max Activating Token Index: 919

Text #16

Max Range: 5.6703. Min Range: -5.6703

Max Act: 5.4515. Min Act: -0.1700

Data Index: 725968 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 5.6703. Min Range: -5.6703

Max Act: 5.4515. Min Act: -0.1700

Data Index: 283165 (C4 (Web Text))

Max Activating Token Index: 535

Text #18

Max Range: 5.6703. Min Range: -5.6703

Max Act: 5.4203. Min Act: -0.1700

Data Index: 184228 (C4 (Web Text))

Max Activating Token Index: 472

Text #19

Max Range: 5.6703. Min Range: -5.6703

Max Act: 5.4515. Min Act: -0.1700

Data Index: 77118 (C4 (Web Text))

Max Activating Token Index: 587