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

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

Neuron 5924 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1897. Min Range: -1.1897

Max Act: 1.1897. Min Act: -0.0000

Data Index: 1590496 (Python Code)

Max Activating Token Index: 986

Text #1

Max Range: 1.1897. Min Range: -1.1897

Max Act: 1.1019. Min Act: -0.0000

Data Index: 1412061 (Python Code)

Max Activating Token Index: 680

Text #2

Max Range: 1.1897. Min Range: -1.1897

Max Act: 1.1382. Min Act: -0.0000

Data Index: 1537027 (Python Code)

Max Activating Token Index: 931

Text #3

Max Range: 1.1897. Min Range: -1.1897

Max Act: 1.0980. Min Act: -0.0000

Data Index: 1459454 (Python Code)

Max Activating Token Index: 583

Text #4

Max Range: 1.1897. Min Range: -1.1897

Max Act: 1.0589. Min Act: -0.0000

Data Index: 1584722 (Python Code)

Max Activating Token Index: 883

Text #5

Max Range: 1.1897. Min Range: -1.1897

Max Act: 1.0013. Min Act: -0.0000

Data Index: 1557442 (Python Code)

Max Activating Token Index: 112

Text #6

Max Range: 1.1897. Min Range: -1.1897

Max Act: 1.0969. Min Act: -0.0000

Data Index: 1563293 (Python Code)

Max Activating Token Index: 130

Text #7

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.9929. Min Act: -0.0000

Data Index: 1505681 (Python Code)

Max Activating Token Index: 606

Text #8

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.9863. Min Act: -0.0000

Data Index: 1398970 (Python Code)

Max Activating Token Index: 109

Text #9

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.9449. Min Act: -0.0000

Data Index: 1560642 (Python Code)

Max Activating Token Index: 313

Text #10

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.8995. Min Act: -0.0000

Data Index: 1346909 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.9555. Min Act: -0.0000

Data Index: 1491687 (Python Code)

Max Activating Token Index: 1021

Text #12

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.9219. Min Act: -0.0000

Data Index: 1409343 (Python Code)

Max Activating Token Index: 590

Text #13

Max Range: 1.1897. Min Range: -1.1897

Max Act: 1.0493. Min Act: -0.0000

Data Index: 1365616 (Python Code)

Max Activating Token Index: 765

Text #14

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.9691. Min Act: -0.0000

Data Index: 203111 (C4 (Web Text))

Max Activating Token Index: 958

Text #15

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.9024. Min Act: -0.0000

Data Index: 1480389 (Python Code)

Max Activating Token Index: 195

Text #16

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.8720. Min Act: -0.0000

Data Index: 1404842 (Python Code)

Max Activating Token Index: 127

Text #17

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.9529. Min Act: -0.0000

Data Index: 1539555 (Python Code)

Max Activating Token Index: 441

Text #18

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.8924. Min Act: -0.0000

Data Index: 1433487 (Python Code)

Max Activating Token Index: 71

Text #19

Max Range: 1.1897. Min Range: -1.1897

Max Act: 0.8744. Min Act: -0.0000

Data Index: 1400183 (Python Code)

Max Activating Token Index: 763