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

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

Neuron 1211 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: 7.8496. Min Range: -7.8496

Max Act: 7.8496. Min Act: -0.1699

Data Index: 34057 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 7.8496. Min Range: -7.8496

Max Act: 7.8496. Min Act: -0.1700

Data Index: 1483328 (Python Code)

Max Activating Token Index: 814

Text #2

Max Range: 7.8496. Min Range: -7.8496

Max Act: 7.6621. Min Act: -0.1700

Data Index: 1643779 (Python Code)

Max Activating Token Index: 685

Text #3

Max Range: 7.8496. Min Range: -7.8496

Max Act: 7.5996. Min Act: -0.1700

Data Index: 1423316 (Python Code)

Max Activating Token Index: 75

Text #4

Max Range: 7.8496. Min Range: -7.8496

Max Act: 7.5996. Min Act: -0.1699

Data Index: 1213837 (C4 (Web Text))

Max Activating Token Index: 988

Text #5

Max Range: 7.8496. Min Range: -7.8496

Max Act: 7.3184. Min Act: -0.1700

Data Index: 935352 (C4 (Web Text))

Max Activating Token Index: 814

Text #6

Max Range: 7.8496. Min Range: -7.8496

Max Act: 7.2559. Min Act: -0.1700

Data Index: 483708 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 7.8496. Min Range: -7.8496

Max Act: 7.2559. Min Act: -0.1700

Data Index: 1439139 (Python Code)

Max Activating Token Index: 151

Text #8

Max Range: 7.8496. Min Range: -7.8496

Max Act: 7.1309. Min Act: -0.1700

Data Index: 1641948 (Python Code)

Max Activating Token Index: 397

Text #9

Max Range: 7.8496. Min Range: -7.8496

Max Act: 6.4746. Min Act: -0.1700

Data Index: 1644387 (Python Code)

Max Activating Token Index: 480

Text #10

Max Range: 7.8496. Min Range: -7.8496

Max Act: 6.2871. Min Act: -0.1699

Data Index: 1524057 (Python Code)

Max Activating Token Index: 692

Text #11

Max Range: 7.8496. Min Range: -7.8496

Max Act: 6.2871. Min Act: -0.1699

Data Index: 1438075 (Python Code)

Max Activating Token Index: 42

Text #12

Max Range: 7.8496. Min Range: -7.8496

Max Act: 6.1621. Min Act: -0.1700

Data Index: 1635757 (Python Code)

Max Activating Token Index: 1022

Text #13

Max Range: 7.8496. Min Range: -7.8496

Max Act: 6.1621. Min Act: -0.1700

Data Index: 1655744 (Python Code)

Max Activating Token Index: 328

Text #14

Max Range: 7.8496. Min Range: -7.8496

Max Act: 6.1309. Min Act: -0.1700

Data Index: 1532639 (Python Code)

Max Activating Token Index: 960

Text #15

Max Range: 7.8496. Min Range: -7.8496

Max Act: 6.0684. Min Act: -0.1700

Data Index: 1414070 (Python Code)

Max Activating Token Index: 914

Text #16

Max Range: 7.8496. Min Range: -7.8496

Max Act: 6.0684. Min Act: -0.1700

Data Index: 1479881 (Python Code)

Max Activating Token Index: 171

Text #17

Max Range: 7.8496. Min Range: -7.8496

Max Act: 6.0996. Min Act: -0.1700

Data Index: 1569846 (Python Code)

Max Activating Token Index: 744

Text #18

Max Range: 7.8496. Min Range: -7.8496

Max Act: 6.0371. Min Act: -0.1700

Data Index: 1526519 (Python Code)

Max Activating Token Index: 627

Text #19

Max Range: 7.8496. Min Range: -7.8496

Max Act: 5.9746. Min Act: -0.1700

Data Index: 1601263 (Python Code)

Max Activating Token Index: 37