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

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

Neuron 1610 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: 5.3813. Min Range: -5.3813

Max Act: 5.3813. Min Act: -0.1700

Data Index: 422419 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 5.3813. Min Range: -5.3813

Max Act: 5.2250. Min Act: -0.1700

Data Index: 131322 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 5.3813. Min Range: -5.3813

Max Act: 5.1625. Min Act: -0.1700

Data Index: 232007 (C4 (Web Text))

Max Activating Token Index: 702

Text #3

Max Range: 5.3813. Min Range: -5.3813

Max Act: 5.1625. Min Act: -0.1700

Data Index: 12783 (C4 (Web Text))

Max Activating Token Index: 522

Text #4

Max Range: 5.3813. Min Range: -5.3813

Max Act: 5.1938. Min Act: -0.1700

Data Index: 920166 (C4 (Web Text))

Max Activating Token Index: 772

Text #5

Max Range: 5.3813. Min Range: -5.3813

Max Act: 5.1000. Min Act: -0.1699

Data Index: 676121 (C4 (Web Text))

Max Activating Token Index: 832

Text #6

Max Range: 5.3813. Min Range: -5.3813

Max Act: 5.1000. Min Act: -0.1700

Data Index: 540551 (C4 (Web Text))

Max Activating Token Index: 369

Text #7

Max Range: 5.3813. Min Range: -5.3813

Max Act: 5.0688. Min Act: -0.1700

Data Index: 900943 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 5.3813. Min Range: -5.3813

Max Act: 5.1313. Min Act: -0.1700

Data Index: 1096906 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 5.3813. Min Range: -5.3813

Max Act: 5.0688. Min Act: -0.1700

Data Index: 1278500 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 5.3813. Min Range: -5.3813

Max Act: 5.0375. Min Act: -0.1700

Data Index: 122276 (C4 (Web Text))

Max Activating Token Index: 406

Text #11

Max Range: 5.3813. Min Range: -5.3813

Max Act: 5.0375. Min Act: -0.1700

Data Index: 241260 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 5.3813. Min Range: -5.3813

Max Act: 5.0375. Min Act: -0.1700

Data Index: 542693 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 5.3813. Min Range: -5.3813

Max Act: 5.0063. Min Act: -0.1700

Data Index: 309936 (C4 (Web Text))

Max Activating Token Index: 517

Text #14

Max Range: 5.3813. Min Range: -5.3813

Max Act: 5.0688. Min Act: -0.1700

Data Index: 444493 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 5.3813. Min Range: -5.3813

Max Act: 5.0063. Min Act: -0.1700

Data Index: 253606 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 5.3813. Min Range: -5.3813

Max Act: 5.0375. Min Act: -0.1700

Data Index: 862110 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 5.3813. Min Range: -5.3813

Max Act: 5.0063. Min Act: -0.1700

Data Index: 401836 (C4 (Web Text))

Max Activating Token Index: 237

Text #18

Max Range: 5.3813. Min Range: -5.3813

Max Act: 5.0375. Min Act: -0.1700

Data Index: 156751 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 5.3813. Min Range: -5.3813

Max Act: 5.0063. Min Act: -0.1700

Data Index: 536972 (C4 (Web Text))

Max Activating Token Index: 308