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

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

Neuron 1537 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: 3.7048. Min Range: -3.7048

Max Act: 3.7048. Min Act: -0.1700

Data Index: 1598474 (Python Code)

Max Activating Token Index: 12

Text #1

Max Range: 3.7048. Min Range: -3.7048

Max Act: 3.6735. Min Act: -0.1700

Data Index: 1485890 (Python Code)

Max Activating Token Index: 8

Text #2

Max Range: 3.7048. Min Range: -3.7048

Max Act: 3.6422. Min Act: -0.1700

Data Index: 1586738 (Python Code)

Max Activating Token Index: 22

Text #3

Max Range: 3.7048. Min Range: -3.7048

Max Act: 3.6109. Min Act: -0.1700

Data Index: 1504844 (Python Code)

Max Activating Token Index: 16

Text #4

Max Range: 3.7048. Min Range: -3.7048

Max Act: 3.6109. Min Act: -0.1700

Data Index: 1418878 (Python Code)

Max Activating Token Index: 179

Text #5

Max Range: 3.7048. Min Range: -3.7048

Max Act: 3.5952. Min Act: -0.1700

Data Index: 1621739 (Python Code)

Max Activating Token Index: 11

Text #6

Max Range: 3.7048. Min Range: -3.7048

Max Act: 3.5639. Min Act: -0.1700

Data Index: 1649423 (Python Code)

Max Activating Token Index: 3

Text #7

Max Range: 3.7048. Min Range: -3.7048

Max Act: 3.5796. Min Act: -0.1700

Data Index: 1481246 (Python Code)

Max Activating Token Index: 19

Text #8

Max Range: 3.7048. Min Range: -3.7048

Max Act: 3.5639. Min Act: -0.1700

Data Index: 1424568 (Python Code)

Max Activating Token Index: 14

Text #9

Max Range: 3.7048. Min Range: -3.7048

Max Act: 3.5639. Min Act: -0.1700

Data Index: 1525099 (Python Code)

Max Activating Token Index: 606

Text #10

Max Range: 3.7048. Min Range: -3.7048

Max Act: 3.5639. Min Act: -0.1700

Data Index: 1430914 (Python Code)

Max Activating Token Index: 166

Text #11

Max Range: 3.7048. Min Range: -3.7048

Max Act: 3.5639. Min Act: -0.1700

Data Index: 1403587 (Python Code)

Max Activating Token Index: 6

Text #12

Max Range: 3.7048. Min Range: -3.7048

Max Act: 3.5639. Min Act: -0.1700

Data Index: 1574936 (Python Code)

Max Activating Token Index: 18

Text #13

Max Range: 3.7048. Min Range: -3.7048

Max Act: 3.5639. Min Act: -0.1700

Data Index: 1497770 (Python Code)

Max Activating Token Index: 465

Text #14

Max Range: 3.7048. Min Range: -3.7048

Max Act: 3.5639. Min Act: -0.1700

Data Index: 1615925 (Python Code)

Max Activating Token Index: 52

Text #15

Max Range: 3.7048. Min Range: -3.7048

Max Act: 3.5482. Min Act: -0.1700

Data Index: 1619080 (Python Code)

Max Activating Token Index: 725

Text #16

Max Range: 3.7048. Min Range: -3.7048

Max Act: 3.5482. Min Act: -0.1700

Data Index: 1428129 (Python Code)

Max Activating Token Index: 51

Text #17

Max Range: 3.7048. Min Range: -3.7048

Max Act: 3.5326. Min Act: -0.1700

Data Index: 1477885 (Python Code)

Max Activating Token Index: 71

Text #18

Max Range: 3.7048. Min Range: -3.7048

Max Act: 3.5326. Min Act: -0.1700

Data Index: 1516100 (Python Code)

Max Activating Token Index: 4

Text #19

Max Range: 3.7048. Min Range: -3.7048

Max Act: 3.5482. Min Act: -0.1700

Data Index: 1623065 (Python Code)

Max Activating Token Index: 32