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

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

Neuron 381 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: 3.1362. Min Range: -3.1362

Max Act: 3.1362. Min Act: -0.1681

Data Index: 53149 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 3.1362. Min Range: -3.1362

Max Act: 3.1046. Min Act: -0.1572

Data Index: 181914 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 3.1362. Min Range: -3.1362

Max Act: 3.0889. Min Act: -0.1698

Data Index: 627612 (C4 (Web Text))

Max Activating Token Index: 825

Text #3

Max Range: 3.1362. Min Range: -3.1362

Max Act: 3.1204. Min Act: -0.1318

Data Index: 1108562 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 3.1362. Min Range: -3.1362

Max Act: 3.0889. Min Act: -0.1697

Data Index: 16302 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 3.1362. Min Range: -3.1362

Max Act: 3.0889. Min Act: -0.1700

Data Index: 1295993 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 3.1362. Min Range: -3.1362

Max Act: 3.0415. Min Act: -0.1698

Data Index: 1352090 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 3.1362. Min Range: -3.1362

Max Act: 3.0257. Min Act: -0.1670

Data Index: 1120916 (C4 (Web Text))

Max Activating Token Index: 483

Text #8

Max Range: 3.1362. Min Range: -3.1362

Max Act: 3.0257. Min Act: -0.1700

Data Index: 1355295 (C4 (Web Text))

Max Activating Token Index: 1012

Text #9

Max Range: 3.1362. Min Range: -3.1362

Max Act: 3.0415. Min Act: -0.1699

Data Index: 937962 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 3.1362. Min Range: -3.1362

Max Act: 3.0415. Min Act: -0.1698

Data Index: 468655 (C4 (Web Text))

Max Activating Token Index: 244

Text #11

Max Range: 3.1362. Min Range: -3.1362

Max Act: 3.0099. Min Act: -0.1318

Data Index: 693304 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 3.1362. Min Range: -3.1362

Max Act: 3.0099. Min Act: -0.1700

Data Index: 600710 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 3.1362. Min Range: -3.1362

Max Act: 2.9941. Min Act: -0.1636

Data Index: 1059036 (C4 (Web Text))

Max Activating Token Index: 319

Text #14

Max Range: 3.1362. Min Range: -3.1362

Max Act: 3.0099. Min Act: -0.1700

Data Index: 619198 (C4 (Web Text))

Max Activating Token Index: 877

Text #15

Max Range: 3.1362. Min Range: -3.1362

Max Act: 3.0257. Min Act: -0.1696

Data Index: 207121 (C4 (Web Text))

Max Activating Token Index: 92

Text #16

Max Range: 3.1362. Min Range: -3.1362

Max Act: 2.9941. Min Act: -0.1699

Data Index: 25999 (C4 (Web Text))

Max Activating Token Index: 896

Text #17

Max Range: 3.1362. Min Range: -3.1362

Max Act: 3.0099. Min Act: -0.1590

Data Index: 598639 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 3.1362. Min Range: -3.1362

Max Act: 2.9783. Min Act: -0.1697

Data Index: 356699 (C4 (Web Text))

Max Activating Token Index: 335

Text #19

Max Range: 3.1362. Min Range: -3.1362

Max Act: 2.9783. Min Act: -0.1700

Data Index: 386288 (C4 (Web Text))

Max Activating Token Index: 98