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

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

Neuron 1634 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5029. Min Range: -3.5029

Max Act: 3.5029. Min Act: -0.0000

Data Index: 1428211 (Python Code)

Max Activating Token Index: 518

Text #1

Max Range: 3.5029. Min Range: -3.5029

Max Act: 2.8905. Min Act: -0.0000

Data Index: 1370159 (Python Code)

Max Activating Token Index: 923

Text #2

Max Range: 3.5029. Min Range: -3.5029

Max Act: 2.8559. Min Act: -0.0000

Data Index: 1531134 (Python Code)

Max Activating Token Index: 47

Text #3

Max Range: 3.5029. Min Range: -3.5029

Max Act: 2.7165. Min Act: -0.0000

Data Index: 1381124 (Python Code)

Max Activating Token Index: 170

Text #4

Max Range: 3.5029. Min Range: -3.5029

Max Act: 2.5306. Min Act: -0.0000

Data Index: 1437728 (Python Code)

Max Activating Token Index: 675

Text #5

Max Range: 3.5029. Min Range: -3.5029

Max Act: 2.6245. Min Act: -0.0000

Data Index: 1419813 (Python Code)

Max Activating Token Index: 828

Text #6

Max Range: 3.5029. Min Range: -3.5029

Max Act: 2.1428. Min Act: -0.0000

Data Index: 1529320 (Python Code)

Max Activating Token Index: 907

Text #7

Max Range: 3.5029. Min Range: -3.5029

Max Act: 2.4509. Min Act: -0.0000

Data Index: 1630342 (Python Code)

Max Activating Token Index: 192

Text #8

Max Range: 3.5029. Min Range: -3.5029

Max Act: 2.3169. Min Act: -0.0000

Data Index: 1649511 (Python Code)

Max Activating Token Index: 505

Text #9

Max Range: 3.5029. Min Range: -3.5029

Max Act: 2.2906. Min Act: -0.0000

Data Index: 1543961 (Python Code)

Max Activating Token Index: 164

Text #10

Max Range: 3.5029. Min Range: -3.5029

Max Act: 2.2721. Min Act: -0.0000

Data Index: 1637334 (Python Code)

Max Activating Token Index: 409

Text #11

Max Range: 3.5029. Min Range: -3.5029

Max Act: 2.3903. Min Act: -0.0000

Data Index: 1573921 (Python Code)

Max Activating Token Index: 983

Text #12

Max Range: 3.5029. Min Range: -3.5029

Max Act: 2.3603. Min Act: -0.0000

Data Index: 1636015 (Python Code)

Max Activating Token Index: 836

Text #13

Max Range: 3.5029. Min Range: -3.5029

Max Act: 2.2438. Min Act: -0.0000

Data Index: 1432474 (Python Code)

Max Activating Token Index: 691

Text #14

Max Range: 3.5029. Min Range: -3.5029

Max Act: 2.3573. Min Act: -0.0000

Data Index: 1534676 (Python Code)

Max Activating Token Index: 42

Text #15

Max Range: 3.5029. Min Range: -3.5029

Max Act: 2.2295. Min Act: -0.0000

Data Index: 1382353 (Python Code)

Max Activating Token Index: 31

Text #16

Max Range: 3.5029. Min Range: -3.5029

Max Act: 2.2062. Min Act: -0.0000

Data Index: 1650418 (Python Code)

Max Activating Token Index: 299

Text #17

Max Range: 3.5029. Min Range: -3.5029

Max Act: 2.2043. Min Act: -0.0000

Data Index: 1612391 (Python Code)

Max Activating Token Index: 923

Text #18

Max Range: 3.5029. Min Range: -3.5029

Max Act: 2.3103. Min Act: -0.0000

Data Index: 1611029 (Python Code)

Max Activating Token Index: 91

Text #19

Max Range: 3.5029. Min Range: -3.5029

Max Act: 2.1922. Min Act: -0.0000

Data Index: 1394332 (Python Code)

Max Activating Token Index: 256