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

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

Neuron 714 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 5.0902. Min Range: -5.0902

Max Act: 5.0277. Min Act: -0.1700

Data Index: 1477453 (Python Code)

Max Activating Token Index: 21

Text #1

Max Range: 5.0902. Min Range: -5.0902

Max Act: 5.0902. Min Act: -0.1700

Data Index: 1521463 (Python Code)

Max Activating Token Index: 38

Text #2

Max Range: 5.0902. Min Range: -5.0902

Max Act: 5.0277. Min Act: -0.1700

Data Index: 1488293 (Python Code)

Max Activating Token Index: 21

Text #3

Max Range: 5.0902. Min Range: -5.0902

Max Act: 5.0277. Min Act: -0.1700

Data Index: 1604647 (Python Code)

Max Activating Token Index: 494

Text #4

Max Range: 5.0902. Min Range: -5.0902

Max Act: 4.9652. Min Act: -0.1700

Data Index: 1526447 (Python Code)

Max Activating Token Index: 21

Text #5

Max Range: 5.0902. Min Range: -5.0902

Max Act: 4.9340. Min Act: -0.1700

Data Index: 1370553 (Python Code)

Max Activating Token Index: 998

Text #6

Max Range: 5.0902. Min Range: -5.0902

Max Act: 4.9652. Min Act: -0.1700

Data Index: 1547773 (Python Code)

Max Activating Token Index: 21

Text #7

Max Range: 5.0902. Min Range: -5.0902

Max Act: 4.9340. Min Act: -0.1700

Data Index: 1456461 (Python Code)

Max Activating Token Index: 20

Text #8

Max Range: 5.0902. Min Range: -5.0902

Max Act: 4.9340. Min Act: -0.1700

Data Index: 1378404 (Python Code)

Max Activating Token Index: 20

Text #9

Max Range: 5.0902. Min Range: -5.0902

Max Act: 4.9652. Min Act: -0.1700

Data Index: 1434883 (Python Code)

Max Activating Token Index: 756

Text #10

Max Range: 5.0902. Min Range: -5.0902

Max Act: 4.9340. Min Act: -0.1700

Data Index: 1392261 (Python Code)

Max Activating Token Index: 20

Text #11

Max Range: 5.0902. Min Range: -5.0902

Max Act: 4.9340. Min Act: -0.1700

Data Index: 1609569 (Python Code)

Max Activating Token Index: 278

Text #12

Max Range: 5.0902. Min Range: -5.0902

Max Act: 4.8715. Min Act: -0.1700

Data Index: 1515606 (Python Code)

Max Activating Token Index: 759

Text #13

Max Range: 5.0902. Min Range: -5.0902

Max Act: 4.9340. Min Act: -0.1700

Data Index: 1530318 (Python Code)

Max Activating Token Index: 448

Text #14

Max Range: 5.0902. Min Range: -5.0902

Max Act: 4.9652. Min Act: -0.1700

Data Index: 1612631 (Python Code)

Max Activating Token Index: 500

Text #15

Max Range: 5.0902. Min Range: -5.0902

Max Act: 4.8715. Min Act: -0.1700

Data Index: 1564517 (Python Code)

Max Activating Token Index: 35

Text #16

Max Range: 5.0902. Min Range: -5.0902

Max Act: 4.8402. Min Act: -0.1700

Data Index: 1647648 (Python Code)

Max Activating Token Index: 951

Text #17

Max Range: 5.0902. Min Range: -5.0902

Max Act: 4.8715. Min Act: -0.1700

Data Index: 1473566 (Python Code)

Max Activating Token Index: 21

Text #18

Max Range: 5.0902. Min Range: -5.0902

Max Act: 4.8715. Min Act: -0.1700

Data Index: 1423261 (Python Code)

Max Activating Token Index: 83

Text #19

Max Range: 5.0902. Min Range: -5.0902

Max Act: 4.8715. Min Act: -0.1700

Data Index: 1593026 (Python Code)

Max Activating Token Index: 21