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

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

Neuron 4350 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9103. Min Range: -1.9103

Max Act: 1.9103. Min Act: -0.0002

Data Index: 1552159 (Python Code)

Max Activating Token Index: 22

Text #1

Max Range: 1.9103. Min Range: -1.9103

Max Act: 1.7118. Min Act: -0.0002

Data Index: 1527630 (Python Code)

Max Activating Token Index: 4

Text #2

Max Range: 1.9103. Min Range: -1.9103

Max Act: 1.5372. Min Act: -0.0002

Data Index: 1653488 (Python Code)

Max Activating Token Index: 238

Text #3

Max Range: 1.9103. Min Range: -1.9103

Max Act: 1.4864. Min Act: -0.0002

Data Index: 1396504 (Python Code)

Max Activating Token Index: 7

Text #4

Max Range: 1.9103. Min Range: -1.9103

Max Act: 1.4336. Min Act: -0.0002

Data Index: 1616416 (Python Code)

Max Activating Token Index: 918

Text #5

Max Range: 1.9103. Min Range: -1.9103

Max Act: 1.3291. Min Act: -0.0002

Data Index: 1636706 (Python Code)

Max Activating Token Index: 657

Text #6

Max Range: 1.9103. Min Range: -1.9103

Max Act: 1.3448. Min Act: -0.0002

Data Index: 1470882 (Python Code)

Max Activating Token Index: 600

Text #7

Max Range: 1.9103. Min Range: -1.9103

Max Act: 1.3266. Min Act: -0.0002

Data Index: 1496500 (Python Code)

Max Activating Token Index: 85

Text #8

Max Range: 1.9103. Min Range: -1.9103

Max Act: 1.2866. Min Act: -0.0002

Data Index: 1445786 (Python Code)

Max Activating Token Index: 420

Text #9

Max Range: 1.9103. Min Range: -1.9103

Max Act: 1.2902. Min Act: -0.0002

Data Index: 1649415 (Python Code)

Max Activating Token Index: 314

Text #10

Max Range: 1.9103. Min Range: -1.9103

Max Act: 1.2664. Min Act: -0.0002

Data Index: 1385823 (Python Code)

Max Activating Token Index: 361

Text #11

Max Range: 1.9103. Min Range: -1.9103

Max Act: 1.2350. Min Act: -0.0002

Data Index: 1436653 (Python Code)

Max Activating Token Index: 146

Text #12

Max Range: 1.9103. Min Range: -1.9103

Max Act: 1.2114. Min Act: -0.0002

Data Index: 1468892 (Python Code)

Max Activating Token Index: 240

Text #13

Max Range: 1.9103. Min Range: -1.9103

Max Act: 1.2737. Min Act: -0.0002

Data Index: 1403713 (Python Code)

Max Activating Token Index: 563

Text #14

Max Range: 1.9103. Min Range: -1.9103

Max Act: 1.2139. Min Act: -0.0002

Data Index: 1455432 (Python Code)

Max Activating Token Index: 158

Text #15

Max Range: 1.9103. Min Range: -1.9103

Max Act: 1.2350. Min Act: -0.0002

Data Index: 1440848 (Python Code)

Max Activating Token Index: 758

Text #16

Max Range: 1.9103. Min Range: -1.9103

Max Act: 1.2018. Min Act: -0.0002

Data Index: 1530108 (Python Code)

Max Activating Token Index: 752

Text #17

Max Range: 1.9103. Min Range: -1.9103

Max Act: 1.1939. Min Act: -0.0002

Data Index: 1510511 (Python Code)

Max Activating Token Index: 833

Text #18

Max Range: 1.9103. Min Range: -1.9103

Max Act: 1.1772. Min Act: -0.0002

Data Index: 1635892 (Python Code)

Max Activating Token Index: 134

Text #19

Max Range: 1.9103. Min Range: -1.9103

Max Act: 1.1739. Min Act: -0.0002

Data Index: 1596320 (Python Code)

Max Activating Token Index: 30