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

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

Neuron 2044 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1274. Min Range: -5.1274

Max Act: 5.1274. Min Act: -0.1697

Data Index: 286682 (C4 (Web Text))

Max Activating Token Index: 472

Text #1

Max Range: 5.1274. Min Range: -5.1274

Max Act: 5.1274. Min Act: -0.1698

Data Index: 1177794 (C4 (Web Text))

Max Activating Token Index: 204

Text #2

Max Range: 5.1274. Min Range: -5.1274

Max Act: 5.0336. Min Act: -0.1700

Data Index: 1072170 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.9711. Min Act: -0.1680

Data Index: 705426 (C4 (Web Text))

Max Activating Token Index: 486

Text #4

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.9711. Min Act: -0.1689

Data Index: 478620 (C4 (Web Text))

Max Activating Token Index: 400

Text #5

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.9399. Min Act: -0.1636

Data Index: 1278214 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.9399. Min Act: -0.1695

Data Index: 397849 (C4 (Web Text))

Max Activating Token Index: 151

Text #7

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.9399. Min Act: -0.1700

Data Index: 712337 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.9086. Min Act: -0.1680

Data Index: 490959 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.8774. Min Act: -0.1700

Data Index: 767692 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.9086. Min Act: -0.1697

Data Index: 1050445 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.8461. Min Act: -0.1700

Data Index: 1039526 (C4 (Web Text))

Max Activating Token Index: 449

Text #12

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.8461. Min Act: -0.1697

Data Index: 682325 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.8149. Min Act: -0.1693

Data Index: 1133041 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.7836. Min Act: -0.1700

Data Index: 786222 (C4 (Web Text))

Max Activating Token Index: 854

Text #15

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.7524. Min Act: -0.1683

Data Index: 447102 (C4 (Web Text))

Max Activating Token Index: 984

Text #16

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.7836. Min Act: -0.1695

Data Index: 230749 (C4 (Web Text))

Max Activating Token Index: 998

Text #17

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.7836. Min Act: -0.1699

Data Index: 810315 (C4 (Web Text))

Max Activating Token Index: 977

Text #18

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.7524. Min Act: -0.1700

Data Index: 1075449 (C4 (Web Text))

Max Activating Token Index: 891

Text #19

Max Range: 5.1274. Min Range: -5.1274

Max Act: 4.7211. Min Act: -0.1690

Data Index: 51365 (C4 (Web Text))

Max Activating Token Index: 445