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

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

Neuron 218 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: 7.2834. Min Range: -7.2834

Max Act: 6.9123. Min Act: -0.0000

Data Index: 1473921 (Python Code)

Max Activating Token Index: 181

Text #1

Max Range: 7.2834. Min Range: -7.2834

Max Act: 7.2834. Min Act: 0.0000

Data Index: 1615407 (Python Code)

Max Activating Token Index: 63

Text #2

Max Range: 7.2834. Min Range: -7.2834

Max Act: 6.9395. Min Act: -0.0000

Data Index: 1605838 (Python Code)

Max Activating Token Index: 375

Text #3

Max Range: 7.2834. Min Range: -7.2834

Max Act: 6.4549. Min Act: -0.0000

Data Index: 1624435 (Python Code)

Max Activating Token Index: 783

Text #4

Max Range: 7.2834. Min Range: -7.2834

Max Act: 6.2652. Min Act: -0.0000

Data Index: 1520810 (Python Code)

Max Activating Token Index: 714

Text #5

Max Range: 7.2834. Min Range: -7.2834

Max Act: 6.0654. Min Act: -0.0000

Data Index: 1625189 (Python Code)

Max Activating Token Index: 558

Text #6

Max Range: 7.2834. Min Range: -7.2834

Max Act: 5.8169. Min Act: -0.0000

Data Index: 1450292 (Python Code)

Max Activating Token Index: 771

Text #7

Max Range: 7.2834. Min Range: -7.2834

Max Act: 6.0110. Min Act: -0.0000

Data Index: 1612429 (Python Code)

Max Activating Token Index: 828

Text #8

Max Range: 7.2834. Min Range: -7.2834

Max Act: 5.5414. Min Act: -0.0000

Data Index: 1405018 (Python Code)

Max Activating Token Index: 792

Text #9

Max Range: 7.2834. Min Range: -7.2834

Max Act: 5.5916. Min Act: -0.0000

Data Index: 1577305 (Python Code)

Max Activating Token Index: 524

Text #10

Max Range: 7.2834. Min Range: -7.2834

Max Act: 5.5752. Min Act: -0.0000

Data Index: 1399036 (Python Code)

Max Activating Token Index: 743

Text #11

Max Range: 7.2834. Min Range: -7.2834

Max Act: 5.5374. Min Act: -0.0000

Data Index: 1560279 (Python Code)

Max Activating Token Index: 976

Text #12

Max Range: 7.2834. Min Range: -7.2834

Max Act: 5.4260. Min Act: -0.0000

Data Index: 1456557 (Python Code)

Max Activating Token Index: 945

Text #13

Max Range: 7.2834. Min Range: -7.2834

Max Act: 5.4091. Min Act: -0.0000

Data Index: 1417413 (Python Code)

Max Activating Token Index: 962

Text #14

Max Range: 7.2834. Min Range: -7.2834

Max Act: 5.1804. Min Act: -0.0000

Data Index: 1578743 (Python Code)

Max Activating Token Index: 145

Text #15

Max Range: 7.2834. Min Range: -7.2834

Max Act: 5.6713. Min Act: -0.0000

Data Index: 1529966 (Python Code)

Max Activating Token Index: 427

Text #16

Max Range: 7.2834. Min Range: -7.2834

Max Act: 5.2993. Min Act: -0.0000

Data Index: 1570526 (Python Code)

Max Activating Token Index: 116

Text #17

Max Range: 7.2834. Min Range: -7.2834

Max Act: 5.2799. Min Act: -0.0000

Data Index: 1648300 (Python Code)

Max Activating Token Index: 769

Text #18

Max Range: 7.2834. Min Range: -7.2834

Max Act: 5.3658. Min Act: -0.0000

Data Index: 1458031 (Python Code)

Max Activating Token Index: 445

Text #19

Max Range: 7.2834. Min Range: -7.2834

Max Act: 5.2294. Min Act: -0.0000

Data Index: 1529147 (Python Code)

Max Activating Token Index: 863