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

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

Neuron 3544 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: 1.1850. Min Range: -1.1850

Max Act: 1.1850. Min Act: -0.0000

Data Index: 1369843 (Python Code)

Max Activating Token Index: 124

Text #1

Max Range: 1.1850. Min Range: -1.1850

Max Act: 1.0841. Min Act: -0.0000

Data Index: 1557708 (Python Code)

Max Activating Token Index: 64

Text #2

Max Range: 1.1850. Min Range: -1.1850

Max Act: 1.0735. Min Act: -0.0000

Data Index: 1523295 (Python Code)

Max Activating Token Index: 727

Text #3

Max Range: 1.1850. Min Range: -1.1850

Max Act: 1.0594. Min Act: -0.0000

Data Index: 1553873 (Python Code)

Max Activating Token Index: 152

Text #4

Max Range: 1.1850. Min Range: -1.1850

Max Act: 1.0534. Min Act: -0.0000

Data Index: 1608184 (Python Code)

Max Activating Token Index: 375

Text #5

Max Range: 1.1850. Min Range: -1.1850

Max Act: 1.0558. Min Act: -0.0000

Data Index: 1450623 (Python Code)

Max Activating Token Index: 172

Text #6

Max Range: 1.1850. Min Range: -1.1850

Max Act: 0.9830. Min Act: -0.0000

Data Index: 1417577 (Python Code)

Max Activating Token Index: 159

Text #7

Max Range: 1.1850. Min Range: -1.1850

Max Act: 0.9636. Min Act: -0.0000

Data Index: 1589733 (Python Code)

Max Activating Token Index: 154

Text #8

Max Range: 1.1850. Min Range: -1.1850

Max Act: 0.9950. Min Act: -0.0000

Data Index: 1513801 (Python Code)

Max Activating Token Index: 488

Text #9

Max Range: 1.1850. Min Range: -1.1850

Max Act: 0.9369. Min Act: -0.0000

Data Index: 1433699 (Python Code)

Max Activating Token Index: 507

Text #10

Max Range: 1.1850. Min Range: -1.1850

Max Act: 0.9364. Min Act: -0.0000

Data Index: 1564771 (Python Code)

Max Activating Token Index: 302

Text #11

Max Range: 1.1850. Min Range: -1.1850

Max Act: 1.0443. Min Act: -0.0000

Data Index: 1360918 (Python Code)

Max Activating Token Index: 298

Text #12

Max Range: 1.1850. Min Range: -1.1850

Max Act: 0.8644. Min Act: -0.0000

Data Index: 1448178 (Python Code)

Max Activating Token Index: 158

Text #13

Max Range: 1.1850. Min Range: -1.1850

Max Act: 0.8155. Min Act: -0.0000

Data Index: 1533992 (Python Code)

Max Activating Token Index: 982

Text #14

Max Range: 1.1850. Min Range: -1.1850

Max Act: 0.9777. Min Act: -0.0000

Data Index: 1620218 (Python Code)

Max Activating Token Index: 62

Text #15

Max Range: 1.1850. Min Range: -1.1850

Max Act: 0.8829. Min Act: -0.0000

Data Index: 1638094 (Python Code)

Max Activating Token Index: 955

Text #16

Max Range: 1.1850. Min Range: -1.1850

Max Act: 0.8070. Min Act: -0.0000

Data Index: 1571928 (Python Code)

Max Activating Token Index: 126

Text #17

Max Range: 1.1850. Min Range: -1.1850

Max Act: 0.9112. Min Act: -0.0000

Data Index: 1425552 (Python Code)

Max Activating Token Index: 512

Text #18

Max Range: 1.1850. Min Range: -1.1850

Max Act: 0.8047. Min Act: -0.0000

Data Index: 1474124 (Python Code)

Max Activating Token Index: 84

Text #19

Max Range: 1.1850. Min Range: -1.1850

Max Act: 0.8211. Min Act: -0.0000

Data Index: 926026 (C4 (Web Text))

Max Activating Token Index: 435