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

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

Neuron 1247 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: 3.2522. Min Range: -3.2522

Max Act: 3.2522. Min Act: -0.1700

Data Index: 1557280 (Python Code)

Max Activating Token Index: 282

Text #1

Max Range: 3.2522. Min Range: -3.2522

Max Act: 3.2050. Min Act: -0.1700

Data Index: 1572440 (Python Code)

Max Activating Token Index: 652

Text #2

Max Range: 3.2522. Min Range: -3.2522

Max Act: 3.2050. Min Act: -0.1700

Data Index: 1395076 (Python Code)

Max Activating Token Index: 1002

Text #3

Max Range: 3.2522. Min Range: -3.2522

Max Act: 3.2208. Min Act: -0.1700

Data Index: 1415662 (Python Code)

Max Activating Token Index: 218

Text #4

Max Range: 3.2522. Min Range: -3.2522

Max Act: 3.1893. Min Act: -0.1700

Data Index: 1529361 (Python Code)

Max Activating Token Index: 979

Text #5

Max Range: 3.2522. Min Range: -3.2522

Max Act: 3.2050. Min Act: -0.1700

Data Index: 1432122 (Python Code)

Max Activating Token Index: 226

Text #6

Max Range: 3.2522. Min Range: -3.2522

Max Act: 3.2050. Min Act: -0.1700

Data Index: 1449318 (Python Code)

Max Activating Token Index: 604

Text #7

Max Range: 3.2522. Min Range: -3.2522

Max Act: 3.1893. Min Act: -0.1700

Data Index: 1519929 (Python Code)

Max Activating Token Index: 666

Text #8

Max Range: 3.2522. Min Range: -3.2522

Max Act: 3.1578. Min Act: -0.1700

Data Index: 1596135 (Python Code)

Max Activating Token Index: 761

Text #9

Max Range: 3.2522. Min Range: -3.2522

Max Act: 3.1736. Min Act: -0.1700

Data Index: 1499246 (Python Code)

Max Activating Token Index: 685

Text #10

Max Range: 3.2522. Min Range: -3.2522

Max Act: 3.1578. Min Act: -0.1700

Data Index: 1533163 (Python Code)

Max Activating Token Index: 383

Text #11

Max Range: 3.2522. Min Range: -3.2522

Max Act: 3.1421. Min Act: -0.1700

Data Index: 1467765 (Python Code)

Max Activating Token Index: 443

Text #12

Max Range: 3.2522. Min Range: -3.2522

Max Act: 3.1421. Min Act: -0.1700

Data Index: 1485067 (Python Code)

Max Activating Token Index: 564

Text #13

Max Range: 3.2522. Min Range: -3.2522

Max Act: 3.1578. Min Act: -0.1700

Data Index: 1473484 (Python Code)

Max Activating Token Index: 750

Text #14

Max Range: 3.2522. Min Range: -3.2522

Max Act: 3.1263. Min Act: -0.1700

Data Index: 1481814 (Python Code)

Max Activating Token Index: 812

Text #15

Max Range: 3.2522. Min Range: -3.2522

Max Act: 3.1421. Min Act: -0.1700

Data Index: 1654286 (Python Code)

Max Activating Token Index: 828

Text #16

Max Range: 3.2522. Min Range: -3.2522

Max Act: 3.0948. Min Act: -0.1700

Data Index: 1407654 (Python Code)

Max Activating Token Index: 798

Text #17

Max Range: 3.2522. Min Range: -3.2522

Max Act: 3.1106. Min Act: -0.1700

Data Index: 1602966 (Python Code)

Max Activating Token Index: 540

Text #18

Max Range: 3.2522. Min Range: -3.2522

Max Act: 3.0948. Min Act: -0.1700

Data Index: 1647613 (Python Code)

Max Activating Token Index: 340

Text #19

Max Range: 3.2522. Min Range: -3.2522

Max Act: 3.1106. Min Act: -0.1700

Data Index: 1532046 (Python Code)

Max Activating Token Index: 186