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

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

Neuron 4834 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5098. Min Range: -1.5098

Max Act: 1.5098. Min Act: -0.0000

Data Index: 1490277 (Python Code)

Max Activating Token Index: 990

Text #1

Max Range: 1.5098. Min Range: -1.5098

Max Act: 1.4723. Min Act: -0.0000

Data Index: 1437524 (Python Code)

Max Activating Token Index: 176

Text #2

Max Range: 1.5098. Min Range: -1.5098

Max Act: 1.3442. Min Act: -0.0000

Data Index: 1650663 (Python Code)

Max Activating Token Index: 204

Text #3

Max Range: 1.5098. Min Range: -1.5098

Max Act: 1.3612. Min Act: -0.0000

Data Index: 1497317 (Python Code)

Max Activating Token Index: 865

Text #4

Max Range: 1.5098. Min Range: -1.5098

Max Act: 1.2275. Min Act: -0.0000

Data Index: 1379142 (Python Code)

Max Activating Token Index: 214

Text #5

Max Range: 1.5098. Min Range: -1.5098

Max Act: 1.1821. Min Act: -0.0000

Data Index: 1409966 (Python Code)

Max Activating Token Index: 807

Text #6

Max Range: 1.5098. Min Range: -1.5098

Max Act: 1.1741. Min Act: 0.0001

Data Index: 1591911 (Python Code)

Max Activating Token Index: 508

Text #7

Max Range: 1.5098. Min Range: -1.5098

Max Act: 1.0731. Min Act: -0.0000

Data Index: 1524355 (Python Code)

Max Activating Token Index: 791

Text #8

Max Range: 1.5098. Min Range: -1.5098

Max Act: 1.1380. Min Act: -0.0000

Data Index: 1499659 (Python Code)

Max Activating Token Index: 351

Text #9

Max Range: 1.5098. Min Range: -1.5098

Max Act: 1.1035. Min Act: -0.0000

Data Index: 1416201 (Python Code)

Max Activating Token Index: 672

Text #10

Max Range: 1.5098. Min Range: -1.5098

Max Act: 1.1582. Min Act: 0.0001

Data Index: 1450851 (Python Code)

Max Activating Token Index: 96

Text #11

Max Range: 1.5098. Min Range: -1.5098

Max Act: 1.0580. Min Act: 0.0000

Data Index: 1517414 (Python Code)

Max Activating Token Index: 456

Text #12

Max Range: 1.5098. Min Range: -1.5098

Max Act: 1.0644. Min Act: -0.0000

Data Index: 1372270 (Python Code)

Max Activating Token Index: 536

Text #13

Max Range: 1.5098. Min Range: -1.5098

Max Act: 1.0536. Min Act: 0.0000

Data Index: 1452387 (Python Code)

Max Activating Token Index: 173

Text #14

Max Range: 1.5098. Min Range: -1.5098

Max Act: 0.9954. Min Act: -0.0000

Data Index: 1515153 (Python Code)

Max Activating Token Index: 967

Text #15

Max Range: 1.5098. Min Range: -1.5098

Max Act: 1.0302. Min Act: 0.0000

Data Index: 1379196 (Python Code)

Max Activating Token Index: 367

Text #16

Max Range: 1.5098. Min Range: -1.5098

Max Act: 0.9937. Min Act: 0.0001

Data Index: 1408905 (Python Code)

Max Activating Token Index: 292

Text #17

Max Range: 1.5098. Min Range: -1.5098

Max Act: 1.0317. Min Act: 0.0000

Data Index: 1382364 (Python Code)

Max Activating Token Index: 847

Text #18

Max Range: 1.5098. Min Range: -1.5098

Max Act: 1.0178. Min Act: -0.0000

Data Index: 1634873 (Python Code)

Max Activating Token Index: 1009

Text #19

Max Range: 1.5098. Min Range: -1.5098

Max Act: 1.0011. Min Act: -0.0000

Data Index: 1618416 (Python Code)

Max Activating Token Index: 371