Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1519 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0631. Min Act: -0.0003

Data Index: 649824 (C4 (Web Text))

Max Activating Token Index: 39

Text #1

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0607. Min Act: -0.0003

Data Index: 402448 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0518. Min Act: -0.0003

Data Index: 123296 (C4 (Web Text))

Max Activating Token Index: 790

Text #3

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0482. Min Act: -0.0003

Data Index: 683863 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0470. Min Act: -0.0003

Data Index: 469710 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0523. Min Act: -0.0003

Data Index: 552789 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0486. Min Act: -0.0003

Data Index: 1281015 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0521. Min Act: -0.0003

Data Index: 807560 (C4 (Web Text))

Max Activating Token Index: 679

Text #8

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0472. Min Act: -0.0003

Data Index: 667667 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0444. Min Act: -0.0003

Data Index: 199311 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0475. Min Act: -0.0003

Data Index: 970014 (C4 (Web Text))

Max Activating Token Index: 819

Text #11

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0486. Min Act: -0.0003

Data Index: 1034976 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0466. Min Act: -0.0003

Data Index: 429631 (C4 (Web Text))

Max Activating Token Index: 513

Text #13

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0414. Min Act: -0.0003

Data Index: 1067173 (C4 (Web Text))

Max Activating Token Index: 507

Text #14

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0453. Min Act: -0.0003

Data Index: 231749 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0451. Min Act: -0.0003

Data Index: 879743 (C4 (Web Text))

Max Activating Token Index: 371

Text #16

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0466. Min Act: -0.0003

Data Index: 329681 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0466. Min Act: -0.0003

Data Index: 88665 (C4 (Web Text))

Max Activating Token Index: 173

Text #18

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0484. Min Act: -0.0003

Data Index: 910335 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 0.0631. Min Range: -0.0631

Max Act: 0.0447. Min Act: -0.0003

Data Index: 1328713 (C4 (Web Text))

Max Activating Token Index: 8