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

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

Neuron 456 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0550. Min Act: -0.0002

Data Index: 34644 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0509. Min Act: -0.0002

Data Index: 376533 (C4 (Web Text))

Max Activating Token Index: 862

Text #2

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0486. Min Act: -0.0002

Data Index: 184629 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0517. Min Act: -0.0002

Data Index: 777733 (C4 (Web Text))

Max Activating Token Index: 64

Text #4

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0493. Min Act: -0.0002

Data Index: 376214 (C4 (Web Text))

Max Activating Token Index: 226

Text #5

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0488. Min Act: -0.0002

Data Index: 864456 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0484. Min Act: -0.0002

Data Index: 725198 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0447. Min Act: -0.0002

Data Index: 357290 (C4 (Web Text))

Max Activating Token Index: 927

Text #8

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0475. Min Act: -0.0002

Data Index: 584140 (C4 (Web Text))

Max Activating Token Index: 684

Text #9

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0473. Min Act: -0.0002

Data Index: 130239 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0477. Min Act: -0.0002

Data Index: 392752 (C4 (Web Text))

Max Activating Token Index: 1017

Text #11

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0467. Min Act: -0.0002

Data Index: 307394 (C4 (Web Text))

Max Activating Token Index: 709

Text #12

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0458. Min Act: -0.0002

Data Index: 484563 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0475. Min Act: -0.0002

Data Index: 864573 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0443. Min Act: -0.0002

Data Index: 618914 (C4 (Web Text))

Max Activating Token Index: 815

Text #15

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0459. Min Act: -0.0002

Data Index: 781702 (C4 (Web Text))

Max Activating Token Index: 949

Text #16

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0444. Min Act: -0.0002

Data Index: 399909 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0453. Min Act: -0.0002

Data Index: 13260 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0446. Min Act: -0.0002

Data Index: 1154781 (C4 (Web Text))

Max Activating Token Index: 220

Text #19

Max Range: 0.0550. Min Range: -0.0550

Max Act: 0.0447. Min Act: -0.0002

Data Index: 1192737 (C4 (Web Text))

Max Activating Token Index: 617