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

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

Neuron 848 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: 3.2526. Min Range: -3.2526

Max Act: 3.2526. Min Act: -0.1700

Data Index: 1616846 (Python Code)

Max Activating Token Index: 953

Text #1

Max Range: 3.2526. Min Range: -3.2526

Max Act: 3.2526. Min Act: -0.1700

Data Index: 1614151 (Python Code)

Max Activating Token Index: 653

Text #2

Max Range: 3.2526. Min Range: -3.2526

Max Act: 3.2369. Min Act: -0.1700

Data Index: 1404757 (Python Code)

Max Activating Token Index: 104

Text #3

Max Range: 3.2526. Min Range: -3.2526

Max Act: 3.2526. Min Act: -0.1700

Data Index: 1377067 (Python Code)

Max Activating Token Index: 105

Text #4

Max Range: 3.2526. Min Range: -3.2526

Max Act: 3.2369. Min Act: -0.1700

Data Index: 1573264 (Python Code)

Max Activating Token Index: 863

Text #5

Max Range: 3.2526. Min Range: -3.2526

Max Act: 3.2212. Min Act: -0.1700

Data Index: 1616145 (Python Code)

Max Activating Token Index: 387

Text #6

Max Range: 3.2526. Min Range: -3.2526

Max Act: 3.2212. Min Act: -0.1700

Data Index: 1459276 (Python Code)

Max Activating Token Index: 105

Text #7

Max Range: 3.2526. Min Range: -3.2526

Max Act: 3.2055. Min Act: -0.1700

Data Index: 1453000 (Python Code)

Max Activating Token Index: 666

Text #8

Max Range: 3.2526. Min Range: -3.2526

Max Act: 3.2055. Min Act: -0.1700

Data Index: 1630713 (Python Code)

Max Activating Token Index: 713

Text #9

Max Range: 3.2526. Min Range: -3.2526

Max Act: 3.2212. Min Act: -0.1700

Data Index: 1376307 (Python Code)

Max Activating Token Index: 15

Text #10

Max Range: 3.2526. Min Range: -3.2526

Max Act: 3.2212. Min Act: -0.1700

Data Index: 1400103 (Python Code)

Max Activating Token Index: 10

Text #11

Max Range: 3.2526. Min Range: -3.2526

Max Act: 3.2055. Min Act: -0.1700

Data Index: 1596374 (Python Code)

Max Activating Token Index: 717

Text #12

Max Range: 3.2526. Min Range: -3.2526

Max Act: 3.1897. Min Act: -0.1700

Data Index: 1362076 (Python Code)

Max Activating Token Index: 793

Text #13

Max Range: 3.2526. Min Range: -3.2526

Max Act: 3.1897. Min Act: -0.1700

Data Index: 1614399 (Python Code)

Max Activating Token Index: 636

Text #14

Max Range: 3.2526. Min Range: -3.2526

Max Act: 3.1740. Min Act: -0.1700

Data Index: 1365917 (Python Code)

Max Activating Token Index: 938

Text #15

Max Range: 3.2526. Min Range: -3.2526

Max Act: 3.1740. Min Act: -0.1700

Data Index: 1497979 (Python Code)

Max Activating Token Index: 264

Text #16

Max Range: 3.2526. Min Range: -3.2526

Max Act: 3.1740. Min Act: -0.1700

Data Index: 1507485 (Python Code)

Max Activating Token Index: 574

Text #17

Max Range: 3.2526. Min Range: -3.2526

Max Act: 3.1740. Min Act: -0.1700

Data Index: 1423987 (Python Code)

Max Activating Token Index: 855

Text #18

Max Range: 3.2526. Min Range: -3.2526

Max Act: 3.1740. Min Act: -0.1700

Data Index: 1425152 (Python Code)

Max Activating Token Index: 517

Text #19

Max Range: 3.2526. Min Range: -3.2526

Max Act: 3.1740. Min Act: -0.1700

Data Index: 1526982 (Python Code)

Max Activating Token Index: 354