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

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

Neuron 1941 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: 5.4991. Min Range: -5.4991

Max Act: 5.4991. Min Act: -0.1700

Data Index: 1651772 (Python Code)

Max Activating Token Index: 651

Text #1

Max Range: 5.4991. Min Range: -5.4991

Max Act: 5.4366. Min Act: -0.1700

Data Index: 1417871 (Python Code)

Max Activating Token Index: 519

Text #2

Max Range: 5.4991. Min Range: -5.4991

Max Act: 5.3741. Min Act: -0.1700

Data Index: 1466575 (Python Code)

Max Activating Token Index: 822

Text #3

Max Range: 5.4991. Min Range: -5.4991

Max Act: 5.4054. Min Act: -0.1700

Data Index: 1543538 (Python Code)

Max Activating Token Index: 896

Text #4

Max Range: 5.4991. Min Range: -5.4991

Max Act: 5.4366. Min Act: -0.1700

Data Index: 1649390 (Python Code)

Max Activating Token Index: 737

Text #5

Max Range: 5.4991. Min Range: -5.4991

Max Act: 5.4054. Min Act: -0.1700

Data Index: 1654837 (Python Code)

Max Activating Token Index: 899

Text #6

Max Range: 5.4991. Min Range: -5.4991

Max Act: 5.3116. Min Act: -0.1700

Data Index: 1518687 (Python Code)

Max Activating Token Index: 953

Text #7

Max Range: 5.4991. Min Range: -5.4991

Max Act: 5.3429. Min Act: -0.1700

Data Index: 1495538 (Python Code)

Max Activating Token Index: 971

Text #8

Max Range: 5.4991. Min Range: -5.4991

Max Act: 5.2804. Min Act: -0.1700

Data Index: 1585036 (Python Code)

Max Activating Token Index: 861

Text #9

Max Range: 5.4991. Min Range: -5.4991

Max Act: 5.2804. Min Act: -0.1700

Data Index: 1363253 (Python Code)

Max Activating Token Index: 817

Text #10

Max Range: 5.4991. Min Range: -5.4991

Max Act: 5.2804. Min Act: -0.1700

Data Index: 1610865 (Python Code)

Max Activating Token Index: 777

Text #11

Max Range: 5.4991. Min Range: -5.4991

Max Act: 5.3116. Min Act: -0.1700

Data Index: 1569338 (Python Code)

Max Activating Token Index: 826

Text #12

Max Range: 5.4991. Min Range: -5.4991

Max Act: 5.3116. Min Act: -0.1700

Data Index: 1397573 (Python Code)

Max Activating Token Index: 839

Text #13

Max Range: 5.4991. Min Range: -5.4991

Max Act: 5.2491. Min Act: -0.1700

Data Index: 1389727 (Python Code)

Max Activating Token Index: 937

Text #14

Max Range: 5.4991. Min Range: -5.4991

Max Act: 5.2491. Min Act: -0.1700

Data Index: 1381497 (Python Code)

Max Activating Token Index: 349

Text #15

Max Range: 5.4991. Min Range: -5.4991

Max Act: 5.2179. Min Act: -0.1700

Data Index: 1374633 (Python Code)

Max Activating Token Index: 362

Text #16

Max Range: 5.4991. Min Range: -5.4991

Max Act: 5.2491. Min Act: -0.1700

Data Index: 1550674 (Python Code)

Max Activating Token Index: 760

Text #17

Max Range: 5.4991. Min Range: -5.4991

Max Act: 5.2179. Min Act: -0.1700

Data Index: 1553485 (Python Code)

Max Activating Token Index: 319

Text #18

Max Range: 5.4991. Min Range: -5.4991

Max Act: 5.2179. Min Act: -0.1700

Data Index: 1511170 (Python Code)

Max Activating Token Index: 967

Text #19

Max Range: 5.4991. Min Range: -5.4991

Max Act: 5.2491. Min Act: -0.1700

Data Index: 1396894 (Python Code)

Max Activating Token Index: 520