Model: GELU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 965 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.4016. Min Range: -3.4016

Max Act: 3.3546. Min Act: -0.1700

Data Index: 1542068 (Python Code)

Max Activating Token Index: 811

Text #1

Max Range: 3.4016. Min Range: -3.4016

Max Act: 3.4016. Min Act: -0.1700

Data Index: 1582171 (Python Code)

Max Activating Token Index: 738

Text #2

Max Range: 3.4016. Min Range: -3.4016

Max Act: 3.3546. Min Act: -0.1700

Data Index: 1640216 (Python Code)

Max Activating Token Index: 45

Text #3

Max Range: 3.4016. Min Range: -3.4016

Max Act: 3.3075. Min Act: -0.1700

Data Index: 1507911 (Python Code)

Max Activating Token Index: 98

Text #4

Max Range: 3.4016. Min Range: -3.4016

Max Act: 3.2918. Min Act: -0.1700

Data Index: 776786 (C4 (Web Text))

Max Activating Token Index: 694

Text #5

Max Range: 3.4016. Min Range: -3.4016

Max Act: 3.3389. Min Act: -0.1700

Data Index: 1389159 (Python Code)

Max Activating Token Index: 394

Text #6

Max Range: 3.4016. Min Range: -3.4016

Max Act: 3.2446. Min Act: -0.1700

Data Index: 193801 (C4 (Web Text))

Max Activating Token Index: 545

Text #7

Max Range: 3.4016. Min Range: -3.4016

Max Act: 3.2603. Min Act: -0.1700

Data Index: 1387078 (Python Code)

Max Activating Token Index: 457

Text #8

Max Range: 3.4016. Min Range: -3.4016

Max Act: 3.2446. Min Act: -0.1700

Data Index: 210511 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 3.4016. Min Range: -3.4016

Max Act: 3.2603. Min Act: -0.1700

Data Index: 1457347 (Python Code)

Max Activating Token Index: 382

Text #10

Max Range: 3.4016. Min Range: -3.4016

Max Act: 3.2603. Min Act: -0.1700

Data Index: 1464583 (Python Code)

Max Activating Token Index: 30

Text #11

Max Range: 3.4016. Min Range: -3.4016

Max Act: 3.2761. Min Act: -0.1700

Data Index: 1634662 (Python Code)

Max Activating Token Index: 221

Text #12

Max Range: 3.4016. Min Range: -3.4016

Max Act: 3.2289. Min Act: -0.1700

Data Index: 1621499 (Python Code)

Max Activating Token Index: 61

Text #13

Max Range: 3.4016. Min Range: -3.4016

Max Act: 3.2132. Min Act: -0.1700

Data Index: 1451665 (Python Code)

Max Activating Token Index: 816

Text #14

Max Range: 3.4016. Min Range: -3.4016

Max Act: 3.2603. Min Act: -0.1700

Data Index: 1305163 (C4 (Web Text))

Max Activating Token Index: 530

Text #15

Max Range: 3.4016. Min Range: -3.4016

Max Act: 3.2289. Min Act: -0.1700

Data Index: 239663 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 3.4016. Min Range: -3.4016

Max Act: 3.2761. Min Act: -0.1700

Data Index: 1254496 (C4 (Web Text))

Max Activating Token Index: 410

Text #17

Max Range: 3.4016. Min Range: -3.4016

Max Act: 3.1660. Min Act: -0.1700

Data Index: 733239 (C4 (Web Text))

Max Activating Token Index: 619

Text #18

Max Range: 3.4016. Min Range: -3.4016

Max Act: 3.3232. Min Act: -0.1700

Data Index: 1597125 (Python Code)

Max Activating Token Index: 696

Text #19

Max Range: 3.4016. Min Range: -3.4016

Max Act: 3.1817. Min Act: -0.1700

Data Index: 1386806 (Python Code)

Max Activating Token Index: 426