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

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

Neuron 315 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: 0.0903. Min Range: -0.0903

Max Act: 0.0903. Min Act: -0.0003

Data Index: 794026 (C4 (Web Text))

Max Activating Token Index: 560

Text #1

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0790. Min Act: -0.0003

Data Index: 116287 (C4 (Web Text))

Max Activating Token Index: 562

Text #2

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0723. Min Act: -0.0003

Data Index: 529974 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0647. Min Act: -0.0002

Data Index: 746388 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0609. Min Act: -0.0003

Data Index: 946671 (C4 (Web Text))

Max Activating Token Index: 622

Text #5

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0682. Min Act: -0.0003

Data Index: 516190 (C4 (Web Text))

Max Activating Token Index: 813

Text #6

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0621. Min Act: -0.0002

Data Index: 330362 (C4 (Web Text))

Max Activating Token Index: 352

Text #7

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0657. Min Act: -0.0003

Data Index: 966705 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0634. Min Act: -0.0003

Data Index: 1037418 (C4 (Web Text))

Max Activating Token Index: 758

Text #9

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0612. Min Act: -0.0003

Data Index: 366171 (C4 (Web Text))

Max Activating Token Index: 384

Text #10

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0644. Min Act: -0.0003

Data Index: 754218 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0607. Min Act: -0.0003

Data Index: 981583 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0600. Min Act: -0.0003

Data Index: 723902 (C4 (Web Text))

Max Activating Token Index: 723

Text #13

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0621. Min Act: -0.0003

Data Index: 915627 (C4 (Web Text))

Max Activating Token Index: 36

Text #14

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0591. Min Act: -0.0003

Data Index: 1039030 (C4 (Web Text))

Max Activating Token Index: 861

Text #15

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0594. Min Act: -0.0003

Data Index: 1047274 (C4 (Web Text))

Max Activating Token Index: 279

Text #16

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0598. Min Act: -0.0003

Data Index: 1321814 (C4 (Web Text))

Max Activating Token Index: 763

Text #17

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0603. Min Act: -0.0003

Data Index: 1268524 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0588. Min Act: -0.0003

Data Index: 1282515 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 0.0903. Min Range: -0.0903

Max Act: 0.0571. Min Act: -0.0003

Data Index: 1196841 (C4 (Web Text))

Max Activating Token Index: 39