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

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

Neuron 1033 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: 1.1578. Min Range: -1.1578

Max Act: 1.1578. Min Act: -0.0000

Data Index: 1397895 (Python Code)

Max Activating Token Index: 1021

Text #1

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.9187. Min Act: -0.0000

Data Index: 1589136 (Python Code)

Max Activating Token Index: 212

Text #2

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.8856. Min Act: -0.0000

Data Index: 1617658 (Python Code)

Max Activating Token Index: 845

Text #3

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.9000. Min Act: -0.0000

Data Index: 1432931 (Python Code)

Max Activating Token Index: 44

Text #4

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.8414. Min Act: -0.0000

Data Index: 1552092 (Python Code)

Max Activating Token Index: 920

Text #5

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.8812. Min Act: -0.0000

Data Index: 1364925 (Python Code)

Max Activating Token Index: 965

Text #6

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.8282. Min Act: -0.0000

Data Index: 1413317 (Python Code)

Max Activating Token Index: 323

Text #7

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.7087. Min Act: -0.0000

Data Index: 1617271 (Python Code)

Max Activating Token Index: 838

Text #8

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.7199. Min Act: -0.0000

Data Index: 1621675 (Python Code)

Max Activating Token Index: 227

Text #9

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.6524. Min Act: -0.0000

Data Index: 1638812 (Python Code)

Max Activating Token Index: 453

Text #10

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.6578. Min Act: -0.0000

Data Index: 1478490 (Python Code)

Max Activating Token Index: 270

Text #11

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.6506. Min Act: -0.0000

Data Index: 1594766 (Python Code)

Max Activating Token Index: 949

Text #12

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.6623. Min Act: -0.0000

Data Index: 1550179 (Python Code)

Max Activating Token Index: 44

Text #13

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.6280. Min Act: -0.0000

Data Index: 1461403 (Python Code)

Max Activating Token Index: 648

Text #14

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.6126. Min Act: -0.0000

Data Index: 1569504 (Python Code)

Max Activating Token Index: 173

Text #15

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.5855. Min Act: -0.0000

Data Index: 1627824 (Python Code)

Max Activating Token Index: 471

Text #16

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.5492. Min Act: -0.0000

Data Index: 1591123 (Python Code)

Max Activating Token Index: 923

Text #17

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.5997. Min Act: -0.0000

Data Index: 1422635 (Python Code)

Max Activating Token Index: 850

Text #18

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.5725. Min Act: -0.0000

Data Index: 1413174 (Python Code)

Max Activating Token Index: 155

Text #19

Max Range: 1.1578. Min Range: -1.1578

Max Act: 0.6195. Min Act: -0.0000

Data Index: 1403520 (Python Code)

Max Activating Token Index: 795