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

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

Neuron 887 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: 0.0888. Min Range: -0.0888

Max Act: 0.0888. Min Act: -0.0003

Data Index: 1319353 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0794. Min Act: -0.0003

Data Index: 103657 (C4 (Web Text))

Max Activating Token Index: 533

Text #2

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0736. Min Act: -0.0003

Data Index: 1203971 (C4 (Web Text))

Max Activating Token Index: 371

Text #3

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0768. Min Act: -0.0003

Data Index: 1102703 (C4 (Web Text))

Max Activating Token Index: 534

Text #4

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0759. Min Act: -0.0003

Data Index: 404444 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0747. Min Act: -0.0003

Data Index: 1176737 (C4 (Web Text))

Max Activating Token Index: 441

Text #6

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0719. Min Act: -0.0003

Data Index: 1077482 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0711. Min Act: -0.0003

Data Index: 866298 (C4 (Web Text))

Max Activating Token Index: 338

Text #8

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0713. Min Act: -0.0002

Data Index: 281213 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0711. Min Act: -0.0003

Data Index: 471115 (C4 (Web Text))

Max Activating Token Index: 539

Text #10

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0655. Min Act: -0.0003

Data Index: 860638 (C4 (Web Text))

Max Activating Token Index: 838

Text #11

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0699. Min Act: -0.0002

Data Index: 532589 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0700. Min Act: -0.0003

Data Index: 1158024 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0669. Min Act: -0.0003

Data Index: 257779 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0692. Min Act: -0.0003

Data Index: 266875 (C4 (Web Text))

Max Activating Token Index: 306

Text #15

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0706. Min Act: -0.0003

Data Index: 756575 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0664. Min Act: -0.0003

Data Index: 1101644 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0642. Min Act: -0.0003

Data Index: 856419 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0675. Min Act: -0.0003

Data Index: 1247629 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 0.0888. Min Range: -0.0888

Max Act: 0.0644. Min Act: -0.0003

Data Index: 1575392 (Python Code)

Max Activating Token Index: 389