Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 254 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0957. Min Act: -0.0003

Data Index: 1623025 (Python Code)

Max Activating Token Index: 436

Text #1

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0892. Min Act: -0.0003

Data Index: 1455985 (Python Code)

Max Activating Token Index: 467

Text #2

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0777. Min Act: -0.0003

Data Index: 1556696 (Python Code)

Max Activating Token Index: 534

Text #3

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0750. Min Act: -0.0003

Data Index: 1555936 (Python Code)

Max Activating Token Index: 445

Text #4

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0748. Min Act: -0.0003

Data Index: 1527390 (Python Code)

Max Activating Token Index: 152

Text #5

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0733. Min Act: -0.0003

Data Index: 1587688 (Python Code)

Max Activating Token Index: 888

Text #6

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0729. Min Act: -0.0003

Data Index: 1607022 (Python Code)

Max Activating Token Index: 375

Text #7

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0743. Min Act: -0.0003

Data Index: 1612593 (Python Code)

Max Activating Token Index: 228

Text #8

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0755. Min Act: -0.0003

Data Index: 1380200 (Python Code)

Max Activating Token Index: 583

Text #9

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0745. Min Act: -0.0003

Data Index: 1362553 (Python Code)

Max Activating Token Index: 401

Text #10

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0758. Min Act: -0.0003

Data Index: 1624040 (Python Code)

Max Activating Token Index: 417

Text #11

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0745. Min Act: -0.0003

Data Index: 1532774 (Python Code)

Max Activating Token Index: 649

Text #12

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0686. Min Act: -0.0003

Data Index: 1607333 (Python Code)

Max Activating Token Index: 786

Text #13

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0767. Min Act: -0.0003

Data Index: 1586421 (Python Code)

Max Activating Token Index: 493

Text #14

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0749. Min Act: -0.0003

Data Index: 1404383 (Python Code)

Max Activating Token Index: 531

Text #15

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0703. Min Act: -0.0003

Data Index: 1622435 (Python Code)

Max Activating Token Index: 169

Text #16

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0714. Min Act: -0.0003

Data Index: 1423827 (Python Code)

Max Activating Token Index: 319

Text #17

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0729. Min Act: -0.0003

Data Index: 1468442 (Python Code)

Max Activating Token Index: 182

Text #18

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0732. Min Act: -0.0003

Data Index: 1613138 (Python Code)

Max Activating Token Index: 368

Text #19

Max Range: 0.0957. Min Range: -0.0957

Max Act: 0.0714. Min Act: -0.0003

Data Index: 1377403 (Python Code)

Max Activating Token Index: 742