Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 80 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0846. Min Act: -0.0005

Data Index: 595713 (C4 (Web Text))

Max Activating Token Index: 504

Text #1

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0775. Min Act: -0.0005

Data Index: 282063 (C4 (Web Text))

Max Activating Token Index: 558

Text #2

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0709. Min Act: -0.0005

Data Index: 1154441 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0723. Min Act: -0.0005

Data Index: 368283 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0688. Min Act: -0.0005

Data Index: 1335433 (C4 (Web Text))

Max Activating Token Index: 305

Text #5

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0680. Min Act: -0.0005

Data Index: 774892 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0717. Min Act: -0.0005

Data Index: 595688 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0635. Min Act: -0.0005

Data Index: 249866 (C4 (Web Text))

Max Activating Token Index: 603

Text #8

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0657. Min Act: -0.0004

Data Index: 1292618 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0636. Min Act: -0.0005

Data Index: 931576 (C4 (Web Text))

Max Activating Token Index: 903

Text #10

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0621. Min Act: -0.0005

Data Index: 453426 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0657. Min Act: -0.0005

Data Index: 148049 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0654. Min Act: -0.0005

Data Index: 30718 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0627. Min Act: -0.0005

Data Index: 99669 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0667. Min Act: -0.0005

Data Index: 17879 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0646. Min Act: -0.0005

Data Index: 1253837 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0664. Min Act: -0.0005

Data Index: 605827 (C4 (Web Text))

Max Activating Token Index: 27

Text #17

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0622. Min Act: -0.0005

Data Index: 433993 (C4 (Web Text))

Max Activating Token Index: 30

Text #18

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0638. Min Act: -0.0005

Data Index: 1251436 (C4 (Web Text))

Max Activating Token Index: 228

Text #19

Max Range: 0.0846. Min Range: -0.0846

Max Act: 0.0657. Min Act: -0.0005

Data Index: 539302 (C4 (Web Text))

Max Activating Token Index: 154