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

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

Neuron 464 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0309. Min Act: -0.0002

Data Index: 1509387 (Python Code)

Max Activating Token Index: 2

Text #1

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0240. Min Act: -0.0003

Data Index: 727625 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0228. Min Act: -0.0003

Data Index: 834877 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0228. Min Act: -0.0002

Data Index: 1570541 (Python Code)

Max Activating Token Index: 2

Text #4

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0228. Min Act: -0.0003

Data Index: 1516503 (Python Code)

Max Activating Token Index: 2

Text #5

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0228. Min Act: -0.0003

Data Index: 1517565 (Python Code)

Max Activating Token Index: 2

Text #6

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0228. Min Act: -0.0002

Data Index: 1606591 (Python Code)

Max Activating Token Index: 2

Text #7

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0228. Min Act: -0.0003

Data Index: 761705 (C4 (Web Text))

Max Activating Token Index: 2

Text #8

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0236. Min Act: -0.0002

Data Index: 798042 (C4 (Web Text))

Max Activating Token Index: 480

Text #9

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0218. Min Act: -0.0003

Data Index: 70471 (C4 (Web Text))

Max Activating Token Index: 439

Text #10

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0212. Min Act: -0.0003

Data Index: 56237 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0212. Min Act: -0.0002

Data Index: 365695 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0206. Min Act: -0.0003

Data Index: 1519454 (Python Code)

Max Activating Token Index: 2

Text #13

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0206. Min Act: -0.0003

Data Index: 461123 (C4 (Web Text))

Max Activating Token Index: 2

Text #14

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0206. Min Act: -0.0003

Data Index: 517055 (C4 (Web Text))

Max Activating Token Index: 2

Text #15

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0191. Min Act: -0.0003

Data Index: 1333382 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0198. Min Act: -0.0002

Data Index: 851961 (C4 (Web Text))

Max Activating Token Index: 2

Text #17

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0201. Min Act: -0.0003

Data Index: 338406 (C4 (Web Text))

Max Activating Token Index: 2

Text #18

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0201. Min Act: -0.0003

Data Index: 742659 (C4 (Web Text))

Max Activating Token Index: 2

Text #19

Max Range: 0.0309. Min Range: -0.0309

Max Act: 0.0201. Min Act: -0.0002

Data Index: 1320069 (C4 (Web Text))

Max Activating Token Index: 2