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

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

Neuron 272 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.7694. Min Act: -0.1700

Data Index: 1570686 (Python Code)

Max Activating Token Index: 5

Text #1

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.6912. Min Act: -0.1700

Data Index: 1524440 (Python Code)

Max Activating Token Index: 22

Text #2

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.6442. Min Act: -0.1700

Data Index: 1399967 (Python Code)

Max Activating Token Index: 10

Text #3

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.6442. Min Act: -0.1700

Data Index: 1545758 (Python Code)

Max Activating Token Index: 10

Text #4

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.6442. Min Act: -0.1700

Data Index: 1569578 (Python Code)

Max Activating Token Index: 106

Text #5

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.6442. Min Act: -0.1700

Data Index: 1528250 (Python Code)

Max Activating Token Index: 728

Text #6

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.6442. Min Act: -0.1700

Data Index: 1367315 (Python Code)

Max Activating Token Index: 366

Text #7

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.6129. Min Act: -0.1700

Data Index: 1377077 (Python Code)

Max Activating Token Index: 992

Text #8

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.6286. Min Act: -0.1700

Data Index: 1468520 (Python Code)

Max Activating Token Index: 601

Text #9

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.5973. Min Act: -0.1700

Data Index: 1359864 (Python Code)

Max Activating Token Index: 28

Text #10

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.6129. Min Act: -0.1700

Data Index: 1555951 (Python Code)

Max Activating Token Index: 8

Text #11

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.5973. Min Act: -0.1700

Data Index: 1585154 (Python Code)

Max Activating Token Index: 409

Text #12

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.6129. Min Act: -0.1700

Data Index: 1484346 (Python Code)

Max Activating Token Index: 575

Text #13

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.5973. Min Act: -0.1700

Data Index: 1589373 (Python Code)

Max Activating Token Index: 32

Text #14

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.5816. Min Act: -0.1700

Data Index: 1391347 (Python Code)

Max Activating Token Index: 813

Text #15

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.5816. Min Act: -0.1700

Data Index: 1530660 (Python Code)

Max Activating Token Index: 175

Text #16

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.5816. Min Act: -0.1700

Data Index: 1532497 (Python Code)

Max Activating Token Index: 947

Text #17

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.5816. Min Act: -0.1700

Data Index: 1414991 (Python Code)

Max Activating Token Index: 8

Text #18

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.5816. Min Act: -0.1700

Data Index: 1407476 (Python Code)

Max Activating Token Index: 468

Text #19

Max Range: 3.7694. Min Range: -3.7694

Max Act: 3.5660. Min Act: -0.1700

Data Index: 1462889 (Python Code)

Max Activating Token Index: 18