Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3861 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0972. Min Act: -0.0002

Data Index: 1563135 (Python Code)

Max Activating Token Index: 805

Text #1

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0777. Min Act: -0.0002

Data Index: 1485267 (Python Code)

Max Activating Token Index: 176

Text #2

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0746. Min Act: -0.0002

Data Index: 1651117 (Python Code)

Max Activating Token Index: 422

Text #3

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0666. Min Act: -0.0002

Data Index: 1364568 (Python Code)

Max Activating Token Index: 797

Text #4

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0676. Min Act: -0.0002

Data Index: 1489903 (Python Code)

Max Activating Token Index: 162

Text #5

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0602. Min Act: -0.0002

Data Index: 1545213 (Python Code)

Max Activating Token Index: 430

Text #6

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0632. Min Act: -0.0002

Data Index: 1375340 (Python Code)

Max Activating Token Index: 592

Text #7

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0587. Min Act: -0.0002

Data Index: 1503604 (Python Code)

Max Activating Token Index: 231

Text #8

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0612. Min Act: -0.0002

Data Index: 1475386 (Python Code)

Max Activating Token Index: 106

Text #9

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0562. Min Act: -0.0002

Data Index: 1605932 (Python Code)

Max Activating Token Index: 299

Text #10

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0556. Min Act: -0.0002

Data Index: 1626974 (Python Code)

Max Activating Token Index: 472

Text #11

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0560. Min Act: -0.0002

Data Index: 1525488 (Python Code)

Max Activating Token Index: 267

Text #12

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0572. Min Act: -0.0002

Data Index: 1549938 (Python Code)

Max Activating Token Index: 107

Text #13

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0575. Min Act: -0.0002

Data Index: 1479797 (Python Code)

Max Activating Token Index: 236

Text #14

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0575. Min Act: -0.0002

Data Index: 1438718 (Python Code)

Max Activating Token Index: 815

Text #15

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0552. Min Act: -0.0002

Data Index: 1610802 (Python Code)

Max Activating Token Index: 246

Text #16

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0552. Min Act: -0.0002

Data Index: 1641901 (Python Code)

Max Activating Token Index: 208

Text #17

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0554. Min Act: -0.0002

Data Index: 1641998 (Python Code)

Max Activating Token Index: 92

Text #18

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0550. Min Act: -0.0002

Data Index: 1485619 (Python Code)

Max Activating Token Index: 550

Text #19

Max Range: 0.0972. Min Range: -0.0972

Max Act: 0.0528. Min Act: -0.0002

Data Index: 1478799 (Python Code)

Max Activating Token Index: 206