Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3200 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.3041. Min Act: -0.0001

Data Index: 1631487 (Python Code)

Max Activating Token Index: 60

Text #1

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.3133. Min Act: -0.0000

Data Index: 720194 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2941. Min Act: -0.0001

Data Index: 1440878 (Python Code)

Max Activating Token Index: 481

Text #3

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2885. Min Act: -0.0001

Data Index: 1504841 (Python Code)

Max Activating Token Index: 78

Text #4

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2658. Min Act: -0.0000

Data Index: 1605917 (Python Code)

Max Activating Token Index: 90

Text #5

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2679. Min Act: -0.0000

Data Index: 1473462 (Python Code)

Max Activating Token Index: 46

Text #6

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2730. Min Act: -0.0001

Data Index: 1551271 (Python Code)

Max Activating Token Index: 38

Text #7

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2626. Min Act: -0.0001

Data Index: 1462519 (Python Code)

Max Activating Token Index: 610

Text #8

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2673. Min Act: -0.0000

Data Index: 1449093 (Python Code)

Max Activating Token Index: 432

Text #9

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2569. Min Act: -0.0001

Data Index: 1574836 (Python Code)

Max Activating Token Index: 241

Text #10

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2527. Min Act: -0.0001

Data Index: 1489959 (Python Code)

Max Activating Token Index: 575

Text #11

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2417. Min Act: -0.0001

Data Index: 1622765 (Python Code)

Max Activating Token Index: 957

Text #12

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2342. Min Act: -0.0001

Data Index: 1468110 (Python Code)

Max Activating Token Index: 190

Text #13

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2571. Min Act: -0.0001

Data Index: 1442598 (Python Code)

Max Activating Token Index: 496

Text #14

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2482. Min Act: -0.0001

Data Index: 1423918 (Python Code)

Max Activating Token Index: 911

Text #15

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2604. Min Act: -0.0001

Data Index: 1515053 (Python Code)

Max Activating Token Index: 880

Text #16

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2348. Min Act: -0.0001

Data Index: 1409086 (Python Code)

Max Activating Token Index: 28

Text #17

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2256. Min Act: -0.0001

Data Index: 1625790 (Python Code)

Max Activating Token Index: 1004

Text #18

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2301. Min Act: -0.0001

Data Index: 1621291 (Python Code)

Max Activating Token Index: 85

Text #19

Max Range: 0.3133. Min Range: -0.3133

Max Act: 0.2053. Min Act: -0.0001

Data Index: 1384889 (Python Code)

Max Activating Token Index: 594