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

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

Neuron 2053 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.7869. Min Act: -0.0000

Data Index: 1531616 (Python Code)

Max Activating Token Index: 673

Text #1

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.7737. Min Act: 0.0000

Data Index: 1384845 (Python Code)

Max Activating Token Index: 337

Text #2

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.5317. Min Act: 0.0000

Data Index: 1598753 (Python Code)

Max Activating Token Index: 48

Text #3

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.5272. Min Act: 0.0001

Data Index: 1401467 (Python Code)

Max Activating Token Index: 19

Text #4

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.4699. Min Act: 0.0001

Data Index: 1444999 (Python Code)

Max Activating Token Index: 72

Text #5

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.3472. Min Act: 0.0000

Data Index: 1613626 (Python Code)

Max Activating Token Index: 129

Text #6

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.3825. Min Act: -0.0000

Data Index: 1506103 (Python Code)

Max Activating Token Index: 55

Text #7

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.3587. Min Act: 0.0000

Data Index: 1625546 (Python Code)

Max Activating Token Index: 46

Text #8

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.4074. Min Act: -0.0000

Data Index: 1361710 (Python Code)

Max Activating Token Index: 39

Text #9

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.3227. Min Act: 0.0001

Data Index: 1460039 (Python Code)

Max Activating Token Index: 324

Text #10

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.3095. Min Act: -0.0000

Data Index: 1472244 (Python Code)

Max Activating Token Index: 368

Text #11

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.3054. Min Act: 0.0001

Data Index: 1428997 (Python Code)

Max Activating Token Index: 51

Text #12

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.3447. Min Act: 0.0001

Data Index: 1465731 (Python Code)

Max Activating Token Index: 83

Text #13

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.2577. Min Act: 0.0001

Data Index: 1447590 (Python Code)

Max Activating Token Index: 16

Text #14

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.1812. Min Act: -0.0000

Data Index: 1449419 (Python Code)

Max Activating Token Index: 23

Text #15

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.2352. Min Act: 0.0000

Data Index: 1646721 (Python Code)

Max Activating Token Index: 13

Text #16

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.2306. Min Act: 0.0000

Data Index: 1569880 (Python Code)

Max Activating Token Index: 661

Text #17

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.2173. Min Act: 0.0000

Data Index: 1496604 (Python Code)

Max Activating Token Index: 62

Text #18

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.1992. Min Act: 0.0000

Data Index: 1653312 (Python Code)

Max Activating Token Index: 30

Text #19

Max Range: 1.7869. Min Range: -1.7869

Max Act: 1.2095. Min Act: -0.0000

Data Index: 1457607 (Python Code)

Max Activating Token Index: 29