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

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

Neuron 320 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: 3.9744. Min Range: -3.9744

Max Act: 3.9744. Min Act: -0.1700

Data Index: 657120 (C4 (Web Text))

Max Activating Token Index: 190

Text #1

Max Range: 3.9744. Min Range: -3.9744

Max Act: 3.8806. Min Act: -0.1700

Data Index: 1189611 (C4 (Web Text))

Max Activating Token Index: 746

Text #2

Max Range: 3.9744. Min Range: -3.9744

Max Act: 3.9119. Min Act: -0.1700

Data Index: 1333647 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 3.9744. Min Range: -3.9744

Max Act: 3.8493. Min Act: -0.1700

Data Index: 843574 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 3.9744. Min Range: -3.9744

Max Act: 3.8337. Min Act: -0.1700

Data Index: 140442 (C4 (Web Text))

Max Activating Token Index: 811

Text #5

Max Range: 3.9744. Min Range: -3.9744

Max Act: 3.8024. Min Act: -0.1700

Data Index: 1335357 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 3.9744. Min Range: -3.9744

Max Act: 3.7868. Min Act: -0.1700

Data Index: 1254404 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 3.9744. Min Range: -3.9744

Max Act: 3.7711. Min Act: -0.1700

Data Index: 1082783 (C4 (Web Text))

Max Activating Token Index: 497

Text #8

Max Range: 3.9744. Min Range: -3.9744

Max Act: 3.7711. Min Act: -0.1700

Data Index: 268808 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 3.9744. Min Range: -3.9744

Max Act: 3.8024. Min Act: -0.1700

Data Index: 25893 (C4 (Web Text))

Max Activating Token Index: 999

Text #10

Max Range: 3.9744. Min Range: -3.9744

Max Act: 3.8024. Min Act: -0.1700

Data Index: 1073316 (C4 (Web Text))

Max Activating Token Index: 540

Text #11

Max Range: 3.9744. Min Range: -3.9744

Max Act: 3.7868. Min Act: -0.1700

Data Index: 665089 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 3.9744. Min Range: -3.9744

Max Act: 3.7711. Min Act: -0.1700

Data Index: 1050851 (C4 (Web Text))

Max Activating Token Index: 894

Text #13

Max Range: 3.9744. Min Range: -3.9744

Max Act: 3.7555. Min Act: -0.1700

Data Index: 115446 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 3.9744. Min Range: -3.9744

Max Act: 3.7868. Min Act: -0.1700

Data Index: 1349028 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 3.9744. Min Range: -3.9744

Max Act: 3.7555. Min Act: -0.1700

Data Index: 517956 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 3.9744. Min Range: -3.9744

Max Act: 3.7399. Min Act: -0.1700

Data Index: 783846 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 3.9744. Min Range: -3.9744

Max Act: 3.7399. Min Act: -0.1700

Data Index: 1248321 (C4 (Web Text))

Max Activating Token Index: 221

Text #18

Max Range: 3.9744. Min Range: -3.9744

Max Act: 3.7555. Min Act: -0.1700

Data Index: 621100 (C4 (Web Text))

Max Activating Token Index: 430

Text #19

Max Range: 3.9744. Min Range: -3.9744

Max Act: 3.7399. Min Act: -0.1700

Data Index: 18700 (C4 (Web Text))

Max Activating Token Index: 309