Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4228 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.9742. Min Act: -0.0000

Data Index: 1549791 (Python Code)

Max Activating Token Index: 362

Text #1

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.9040. Min Act: -0.0000

Data Index: 1391000 (Python Code)

Max Activating Token Index: 699

Text #2

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.8623. Min Act: -0.0000

Data Index: 1590699 (Python Code)

Max Activating Token Index: 319

Text #3

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.7527. Min Act: -0.0000

Data Index: 1375959 (Python Code)

Max Activating Token Index: 657

Text #4

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.6606. Min Act: -0.0000

Data Index: 1410499 (Python Code)

Max Activating Token Index: 951

Text #5

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.6584. Min Act: -0.0000

Data Index: 1421598 (Python Code)

Max Activating Token Index: 241

Text #6

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.5749. Min Act: -0.0000

Data Index: 1052396 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.6274. Min Act: 0.0000

Data Index: 1518746 (Python Code)

Max Activating Token Index: 643

Text #8

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.6151. Min Act: 0.0001

Data Index: 1450141 (Python Code)

Max Activating Token Index: 131

Text #9

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.6183. Min Act: -0.0000

Data Index: 1377343 (Python Code)

Max Activating Token Index: 332

Text #10

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.6177. Min Act: -0.0000

Data Index: 1631593 (Python Code)

Max Activating Token Index: 391

Text #11

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.6265. Min Act: -0.0000

Data Index: 1613120 (Python Code)

Max Activating Token Index: 540

Text #12

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.6026. Min Act: -0.0000

Data Index: 1580356 (Python Code)

Max Activating Token Index: 168

Text #13

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.5953. Min Act: -0.0000

Data Index: 1540096 (Python Code)

Max Activating Token Index: 164

Text #14

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.5897. Min Act: -0.0000

Data Index: 1450466 (Python Code)

Max Activating Token Index: 601

Text #15

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.5698. Min Act: -0.0000

Data Index: 1597680 (Python Code)

Max Activating Token Index: 622

Text #16

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.5825. Min Act: -0.0000

Data Index: 1520079 (Python Code)

Max Activating Token Index: 872

Text #17

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.5466. Min Act: -0.0000

Data Index: 192750 (C4 (Web Text))

Max Activating Token Index: 420

Text #18

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.5583. Min Act: -0.0000

Data Index: 16129 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 0.9742. Min Range: -0.9742

Max Act: 0.5993. Min Act: -0.0000

Data Index: 1361524 (Python Code)

Max Activating Token Index: 94