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

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

Neuron 4985 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: 2.3804. Min Range: -2.3804

Max Act: 2.3804. Min Act: -0.0000

Data Index: 1561703 (Python Code)

Max Activating Token Index: 721

Text #1

Max Range: 2.3804. Min Range: -2.3804

Max Act: 2.0859. Min Act: -0.0000

Data Index: 1086211 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 2.3804. Min Range: -2.3804

Max Act: 2.0275. Min Act: -0.0000

Data Index: 159130 (C4 (Web Text))

Max Activating Token Index: 528

Text #3

Max Range: 2.3804. Min Range: -2.3804

Max Act: 2.1059. Min Act: -0.0000

Data Index: 1638364 (Python Code)

Max Activating Token Index: 621

Text #4

Max Range: 2.3804. Min Range: -2.3804

Max Act: 1.8242. Min Act: -0.0000

Data Index: 1220381 (C4 (Web Text))

Max Activating Token Index: 276

Text #5

Max Range: 2.3804. Min Range: -2.3804

Max Act: 1.7778. Min Act: -0.0000

Data Index: 1370303 (Python Code)

Max Activating Token Index: 912

Text #6

Max Range: 2.3804. Min Range: -2.3804

Max Act: 1.7922. Min Act: -0.0000

Data Index: 468066 (C4 (Web Text))

Max Activating Token Index: 301

Text #7

Max Range: 2.3804. Min Range: -2.3804

Max Act: 1.7034. Min Act: -0.0000

Data Index: 605288 (C4 (Web Text))

Max Activating Token Index: 543

Text #8

Max Range: 2.3804. Min Range: -2.3804

Max Act: 1.7798. Min Act: -0.0000

Data Index: 1474197 (Python Code)

Max Activating Token Index: 737

Text #9

Max Range: 2.3804. Min Range: -2.3804

Max Act: 1.7856. Min Act: -0.0000

Data Index: 84578 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 2.3804. Min Range: -2.3804

Max Act: 1.6574. Min Act: -0.0000

Data Index: 1557162 (Python Code)

Max Activating Token Index: 919

Text #11

Max Range: 2.3804. Min Range: -2.3804

Max Act: 1.7530. Min Act: -0.0000

Data Index: 197424 (C4 (Web Text))

Max Activating Token Index: 63

Text #12

Max Range: 2.3804. Min Range: -2.3804

Max Act: 1.7269. Min Act: -0.0000

Data Index: 1539278 (Python Code)

Max Activating Token Index: 462

Text #13

Max Range: 2.3804. Min Range: -2.3804

Max Act: 1.7184. Min Act: -0.0000

Data Index: 1622100 (Python Code)

Max Activating Token Index: 638

Text #14

Max Range: 2.3804. Min Range: -2.3804

Max Act: 1.8047. Min Act: -0.0000

Data Index: 537262 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 2.3804. Min Range: -2.3804

Max Act: 1.5028. Min Act: -0.0000

Data Index: 727507 (C4 (Web Text))

Max Activating Token Index: 712

Text #16

Max Range: 2.3804. Min Range: -2.3804

Max Act: 1.6825. Min Act: -0.0000

Data Index: 1544451 (Python Code)

Max Activating Token Index: 358

Text #17

Max Range: 2.3804. Min Range: -2.3804

Max Act: 1.5917. Min Act: -0.0000

Data Index: 1405507 (Python Code)

Max Activating Token Index: 131

Text #18

Max Range: 2.3804. Min Range: -2.3804

Max Act: 1.5712. Min Act: -0.0000

Data Index: 1360672 (Python Code)

Max Activating Token Index: 815

Text #19

Max Range: 2.3804. Min Range: -2.3804

Max Act: 1.6578. Min Act: -0.0000

Data Index: 1628965 (Python Code)

Max Activating Token Index: 56