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

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

Neuron 190 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.3857. Min Act: -0.1700

Data Index: 1446596 (Python Code)

Max Activating Token Index: 505

Text #1

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.3857. Min Act: -0.1700

Data Index: 1365196 (Python Code)

Max Activating Token Index: 912

Text #2

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.3700. Min Act: -0.1700

Data Index: 1414251 (Python Code)

Max Activating Token Index: 481

Text #3

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.3857. Min Act: -0.1700

Data Index: 1516349 (Python Code)

Max Activating Token Index: 849

Text #4

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.3386. Min Act: -0.1700

Data Index: 1533305 (Python Code)

Max Activating Token Index: 999

Text #5

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.3386. Min Act: -0.1700

Data Index: 1613916 (Python Code)

Max Activating Token Index: 976

Text #6

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.3229. Min Act: -0.1700

Data Index: 1557577 (Python Code)

Max Activating Token Index: 1016

Text #7

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.2758. Min Act: -0.1700

Data Index: 1627702 (Python Code)

Max Activating Token Index: 885

Text #8

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.3072. Min Act: -0.1700

Data Index: 1498502 (Python Code)

Max Activating Token Index: 344

Text #9

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.2915. Min Act: -0.1700

Data Index: 1371503 (Python Code)

Max Activating Token Index: 655

Text #10

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.2758. Min Act: -0.1700

Data Index: 1459872 (Python Code)

Max Activating Token Index: 723

Text #11

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.2601. Min Act: -0.1700

Data Index: 1554014 (Python Code)

Max Activating Token Index: 992

Text #12

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.2601. Min Act: -0.1700

Data Index: 1539980 (Python Code)

Max Activating Token Index: 867

Text #13

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.2758. Min Act: -0.1700

Data Index: 1536080 (Python Code)

Max Activating Token Index: 974

Text #14

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.2601. Min Act: -0.1700

Data Index: 1400771 (Python Code)

Max Activating Token Index: 733

Text #15

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.2758. Min Act: -0.1700

Data Index: 1451349 (Python Code)

Max Activating Token Index: 390

Text #16

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.2758. Min Act: -0.1700

Data Index: 1514776 (Python Code)

Max Activating Token Index: 943

Text #17

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.3229. Min Act: -0.1700

Data Index: 1479586 (Python Code)

Max Activating Token Index: 889

Text #18

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.2758. Min Act: -0.1700

Data Index: 1605278 (Python Code)

Max Activating Token Index: 605

Text #19

Max Range: 3.3857. Min Range: -3.3857

Max Act: 3.2601. Min Act: -0.1700

Data Index: 1403382 (Python Code)

Max Activating Token Index: 901