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

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

Neuron 2106 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5753. Min Range: -2.5753

Max Act: 2.5753. Min Act: -0.0000

Data Index: 1508068 (Python Code)

Max Activating Token Index: 46

Text #1

Max Range: 2.5753. Min Range: -2.5753

Max Act: 2.5195. Min Act: -0.0000

Data Index: 1438671 (Python Code)

Max Activating Token Index: 528

Text #2

Max Range: 2.5753. Min Range: -2.5753

Max Act: 2.4421. Min Act: -0.0000

Data Index: 474754 (C4 (Web Text))

Max Activating Token Index: 18

Text #3

Max Range: 2.5753. Min Range: -2.5753

Max Act: 2.4261. Min Act: -0.0000

Data Index: 1578438 (Python Code)

Max Activating Token Index: 130

Text #4

Max Range: 2.5753. Min Range: -2.5753

Max Act: 2.3877. Min Act: -0.0000

Data Index: 1586048 (Python Code)

Max Activating Token Index: 270

Text #5

Max Range: 2.5753. Min Range: -2.5753

Max Act: 2.2464. Min Act: -0.0000

Data Index: 1595073 (Python Code)

Max Activating Token Index: 454

Text #6

Max Range: 2.5753. Min Range: -2.5753

Max Act: 2.3115. Min Act: -0.0000

Data Index: 1432020 (Python Code)

Max Activating Token Index: 660

Text #7

Max Range: 2.5753. Min Range: -2.5753

Max Act: 2.2289. Min Act: -0.0000

Data Index: 1477536 (Python Code)

Max Activating Token Index: 254

Text #8

Max Range: 2.5753. Min Range: -2.5753

Max Act: 2.1882. Min Act: -0.0000

Data Index: 1464354 (Python Code)

Max Activating Token Index: 177

Text #9

Max Range: 2.5753. Min Range: -2.5753

Max Act: 2.2953. Min Act: -0.0000

Data Index: 195895 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 2.5753. Min Range: -2.5753

Max Act: 2.1843. Min Act: -0.0000

Data Index: 1497322 (Python Code)

Max Activating Token Index: 815

Text #11

Max Range: 2.5753. Min Range: -2.5753

Max Act: 2.1468. Min Act: -0.0000

Data Index: 1418143 (Python Code)

Max Activating Token Index: 991

Text #12

Max Range: 2.5753. Min Range: -2.5753

Max Act: 2.1381. Min Act: -0.0000

Data Index: 1616813 (Python Code)

Max Activating Token Index: 993

Text #13

Max Range: 2.5753. Min Range: -2.5753

Max Act: 2.0154. Min Act: -0.0000

Data Index: 706834 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 2.5753. Min Range: -2.5753

Max Act: 2.1281. Min Act: -0.0000

Data Index: 1509748 (Python Code)

Max Activating Token Index: 315

Text #15

Max Range: 2.5753. Min Range: -2.5753

Max Act: 2.0108. Min Act: -0.0000

Data Index: 1532000 (Python Code)

Max Activating Token Index: 226

Text #16

Max Range: 2.5753. Min Range: -2.5753

Max Act: 2.2486. Min Act: -0.0000

Data Index: 1411354 (Python Code)

Max Activating Token Index: 365

Text #17

Max Range: 2.5753. Min Range: -2.5753

Max Act: 1.9942. Min Act: -0.0000

Data Index: 1655172 (Python Code)

Max Activating Token Index: 443

Text #18

Max Range: 2.5753. Min Range: -2.5753

Max Act: 2.1004. Min Act: -0.0000

Data Index: 1645971 (Python Code)

Max Activating Token Index: 111

Text #19

Max Range: 2.5753. Min Range: -2.5753

Max Act: 2.0975. Min Act: -0.0000

Data Index: 1638372 (Python Code)

Max Activating Token Index: 125