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

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

Neuron 923 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.3654. Min Act: -0.1700

Data Index: 502661 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.3026. Min Act: -0.1700

Data Index: 1283727 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.2397. Min Act: -0.1700

Data Index: 1082485 (C4 (Web Text))

Max Activating Token Index: 465

Text #3

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.2240. Min Act: -0.1700

Data Index: 614650 (C4 (Web Text))

Max Activating Token Index: 278

Text #4

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.1768. Min Act: -0.1700

Data Index: 1335227 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.1926. Min Act: -0.1700

Data Index: 1336050 (C4 (Web Text))

Max Activating Token Index: 783

Text #6

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.1611. Min Act: -0.1700

Data Index: 681282 (C4 (Web Text))

Max Activating Token Index: 763

Text #7

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.2083. Min Act: -0.1700

Data Index: 1321487 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.1611. Min Act: -0.1700

Data Index: 1196946 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.1611. Min Act: -0.1700

Data Index: 206674 (C4 (Web Text))

Max Activating Token Index: 81

Text #10

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.1296. Min Act: -0.1700

Data Index: 381637 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.1453. Min Act: -0.1700

Data Index: 484773 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.1611. Min Act: -0.1700

Data Index: 801144 (C4 (Web Text))

Max Activating Token Index: 718

Text #13

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.1453. Min Act: -0.1700

Data Index: 968886 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.1296. Min Act: -0.1700

Data Index: 1068842 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.1296. Min Act: -0.1700

Data Index: 37041 (C4 (Web Text))

Max Activating Token Index: 251

Text #16

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.1296. Min Act: -0.1700

Data Index: 315893 (C4 (Web Text))

Max Activating Token Index: 108

Text #17

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.1453. Min Act: -0.1700

Data Index: 389896 (C4 (Web Text))

Max Activating Token Index: 447

Text #18

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.1296. Min Act: -0.1700

Data Index: 178001 (C4 (Web Text))

Max Activating Token Index: 750

Text #19

Max Range: 3.3654. Min Range: -3.3654

Max Act: 3.1138. Min Act: -0.1700

Data Index: 10447 (C4 (Web Text))

Max Activating Token Index: 60