Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1533 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.8546. Min Range: -3.8546

Max Act: 3.7295. Min Act: -0.1700

Data Index: 139843 (C4 (Web Text))

Max Activating Token Index: 446

Text #1

Max Range: 3.8546. Min Range: -3.8546

Max Act: 3.8233. Min Act: -0.1700

Data Index: 660252 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 3.8546. Min Range: -3.8546

Max Act: 3.8233. Min Act: -0.1699

Data Index: 1146778 (C4 (Web Text))

Max Activating Token Index: 587

Text #3

Max Range: 3.8546. Min Range: -3.8546

Max Act: 3.8546. Min Act: -0.1700

Data Index: 51151 (C4 (Web Text))

Max Activating Token Index: 628

Text #4

Max Range: 3.8546. Min Range: -3.8546

Max Act: 3.7921. Min Act: -0.1700

Data Index: 190593 (C4 (Web Text))

Max Activating Token Index: 784

Text #5

Max Range: 3.8546. Min Range: -3.8546

Max Act: 3.7608. Min Act: -0.1700

Data Index: 140090 (C4 (Web Text))

Max Activating Token Index: 142

Text #6

Max Range: 3.8546. Min Range: -3.8546

Max Act: 3.6669. Min Act: -0.1700

Data Index: 1095091 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 3.8546. Min Range: -3.8546

Max Act: 3.6669. Min Act: -0.1700

Data Index: 1345926 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 3.8546. Min Range: -3.8546

Max Act: 3.6356. Min Act: -0.1700

Data Index: 1122730 (C4 (Web Text))

Max Activating Token Index: 173

Text #9

Max Range: 3.8546. Min Range: -3.8546

Max Act: 3.6043. Min Act: -0.1700

Data Index: 1275228 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 3.8546. Min Range: -3.8546

Max Act: 3.6356. Min Act: -0.1700

Data Index: 848197 (C4 (Web Text))

Max Activating Token Index: 891

Text #11

Max Range: 3.8546. Min Range: -3.8546

Max Act: 3.6043. Min Act: -0.1700

Data Index: 840028 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 3.8546. Min Range: -3.8546

Max Act: 3.6043. Min Act: -0.1700

Data Index: 422077 (C4 (Web Text))

Max Activating Token Index: 536

Text #13

Max Range: 3.8546. Min Range: -3.8546

Max Act: 3.6043. Min Act: -0.1700

Data Index: 738311 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 3.8546. Min Range: -3.8546

Max Act: 3.6043. Min Act: -0.1700

Data Index: 17854 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 3.8546. Min Range: -3.8546

Max Act: 3.5416. Min Act: -0.1700

Data Index: 1209919 (C4 (Web Text))

Max Activating Token Index: 820

Text #16

Max Range: 3.8546. Min Range: -3.8546

Max Act: 3.6043. Min Act: -0.1700

Data Index: 915415 (C4 (Web Text))

Max Activating Token Index: 115

Text #17

Max Range: 3.8546. Min Range: -3.8546

Max Act: 3.5730. Min Act: -0.1699

Data Index: 1162278 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 3.8546. Min Range: -3.8546

Max Act: 3.5730. Min Act: -0.1700

Data Index: 1196091 (C4 (Web Text))

Max Activating Token Index: 836

Text #19

Max Range: 3.8546. Min Range: -3.8546

Max Act: 3.5416. Min Act: -0.1700

Data Index: 696610 (C4 (Web Text))

Max Activating Token Index: 438