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

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

Neuron 2607 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: 0.0479. Min Range: -0.0479

Max Act: 0.0479. Min Act: -0.0003

Data Index: 750577 (C4 (Web Text))

Max Activating Token Index: 372

Text #1

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0450. Min Act: -0.0003

Data Index: 285471 (C4 (Web Text))

Max Activating Token Index: 820

Text #2

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0431. Min Act: -0.0003

Data Index: 830473 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0432. Min Act: -0.0003

Data Index: 992354 (C4 (Web Text))

Max Activating Token Index: 169

Text #4

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0420. Min Act: -0.0003

Data Index: 676444 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0418. Min Act: -0.0003

Data Index: 844436 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0407. Min Act: -0.0003

Data Index: 1037879 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0391. Min Act: -0.0003

Data Index: 404382 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0403. Min Act: -0.0003

Data Index: 426545 (C4 (Web Text))

Max Activating Token Index: 316

Text #9

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0381. Min Act: -0.0003

Data Index: 832080 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0396. Min Act: -0.0003

Data Index: 601926 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0406. Min Act: -0.0003

Data Index: 67660 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0337. Min Act: -0.0003

Data Index: 260031 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0370. Min Act: -0.0003

Data Index: 522039 (C4 (Web Text))

Max Activating Token Index: 843

Text #14

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0377. Min Act: -0.0003

Data Index: 1210735 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0382. Min Act: -0.0003

Data Index: 608789 (C4 (Web Text))

Max Activating Token Index: 833

Text #16

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0371. Min Act: -0.0003

Data Index: 838412 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0384. Min Act: -0.0003

Data Index: 365862 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0389. Min Act: -0.0003

Data Index: 193703 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 0.0479. Min Range: -0.0479

Max Act: 0.0371. Min Act: -0.0003

Data Index: 505537 (C4 (Web Text))

Max Activating Token Index: 972