Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 875 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 3.9654. Min Range: -3.9654

Max Act: 3.9654. Min Act: -0.1700

Data Index: 1640617 (Python Code)

Max Activating Token Index: 109

Text #1

Max Range: 3.9654. Min Range: -3.9654

Max Act: 3.7777. Min Act: -0.1700

Data Index: 1491195 (Python Code)

Max Activating Token Index: 280

Text #2

Max Range: 3.9654. Min Range: -3.9654

Max Act: 3.6838. Min Act: -0.1699

Data Index: 1628800 (Python Code)

Max Activating Token Index: 858

Text #3

Max Range: 3.9654. Min Range: -3.9654

Max Act: 3.6838. Min Act: -0.1700

Data Index: 1389396 (Python Code)

Max Activating Token Index: 787

Text #4

Max Range: 3.9654. Min Range: -3.9654

Max Act: 3.6838. Min Act: -0.1692

Data Index: 1477729 (Python Code)

Max Activating Token Index: 395

Text #5

Max Range: 3.9654. Min Range: -3.9654

Max Act: 3.6838. Min Act: -0.1700

Data Index: 1611316 (Python Code)

Max Activating Token Index: 709

Text #6

Max Range: 3.9654. Min Range: -3.9654

Max Act: 3.5899. Min Act: -0.1696

Data Index: 1577604 (Python Code)

Max Activating Token Index: 37

Text #7

Max Range: 3.9654. Min Range: -3.9654

Max Act: 3.6212. Min Act: -0.1700

Data Index: 1446369 (Python Code)

Max Activating Token Index: 318

Text #8

Max Range: 3.9654. Min Range: -3.9654

Max Act: 3.5899. Min Act: -0.1699

Data Index: 1515051 (Python Code)

Max Activating Token Index: 677

Text #9

Max Range: 3.9654. Min Range: -3.9654

Max Act: 3.6525. Min Act: -0.1700

Data Index: 1467402 (Python Code)

Max Activating Token Index: 132

Text #10

Max Range: 3.9654. Min Range: -3.9654

Max Act: 3.6212. Min Act: -0.1699

Data Index: 1546823 (Python Code)

Max Activating Token Index: 772

Text #11

Max Range: 3.9654. Min Range: -3.9654

Max Act: 3.5586. Min Act: -0.1389

Data Index: 1542119 (Python Code)

Max Activating Token Index: 212

Text #12

Max Range: 3.9654. Min Range: -3.9654

Max Act: 3.5586. Min Act: -0.1700

Data Index: 1646814 (Python Code)

Max Activating Token Index: 653

Text #13

Max Range: 3.9654. Min Range: -3.9654

Max Act: 3.5586. Min Act: -0.1700

Data Index: 1461525 (Python Code)

Max Activating Token Index: 251

Text #14

Max Range: 3.9654. Min Range: -3.9654

Max Act: 3.5273. Min Act: -0.1700

Data Index: 1577989 (Python Code)

Max Activating Token Index: 300

Text #15

Max Range: 3.9654. Min Range: -3.9654

Max Act: 3.5273. Min Act: -0.1529

Data Index: 1634925 (Python Code)

Max Activating Token Index: 657

Text #16

Max Range: 3.9654. Min Range: -3.9654

Max Act: 3.5586. Min Act: -0.1698

Data Index: 1631219 (Python Code)

Max Activating Token Index: 552

Text #17

Max Range: 3.9654. Min Range: -3.9654

Max Act: 3.4959. Min Act: -0.1698

Data Index: 1613205 (Python Code)

Max Activating Token Index: 171

Text #18

Max Range: 3.9654. Min Range: -3.9654

Max Act: 3.5586. Min Act: -0.1699

Data Index: 995464 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 3.9654. Min Range: -3.9654

Max Act: 3.4959. Min Act: -0.1689

Data Index: 1457131 (Python Code)

Max Activating Token Index: 432