Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 15 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0979. Min Act: -0.0001

Data Index: 597498 (C4 (Web Text))

Max Activating Token Index: 391

Text #1

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0879. Min Act: -0.0001

Data Index: 402264 (C4 (Web Text))

Max Activating Token Index: 433

Text #2

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0667. Min Act: -0.0001

Data Index: 819773 (C4 (Web Text))

Max Activating Token Index: 831

Text #3

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0526. Min Act: -0.0001

Data Index: 214211 (C4 (Web Text))

Max Activating Token Index: 960

Text #4

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0505. Min Act: -0.0001

Data Index: 376960 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0472. Min Act: -0.0001

Data Index: 1348209 (C4 (Web Text))

Max Activating Token Index: 546

Text #6

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0490. Min Act: -0.0001

Data Index: 752609 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0494. Min Act: -0.0001

Data Index: 244557 (C4 (Web Text))

Max Activating Token Index: 647

Text #8

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0494. Min Act: -0.0001

Data Index: 165409 (C4 (Web Text))

Max Activating Token Index: 473

Text #9

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0453. Min Act: -0.0001

Data Index: 1256796 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0427. Min Act: -0.0001

Data Index: 30798 (C4 (Web Text))

Max Activating Token Index: 300

Text #11

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0467. Min Act: -0.0001

Data Index: 191111 (C4 (Web Text))

Max Activating Token Index: 988

Text #12

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0424. Min Act: -0.0001

Data Index: 429104 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0454. Min Act: -0.0001

Data Index: 846314 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0429. Min Act: -0.0001

Data Index: 455506 (C4 (Web Text))

Max Activating Token Index: 309

Text #15

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0398. Min Act: -0.0001

Data Index: 6764 (C4 (Web Text))

Max Activating Token Index: 729

Text #16

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0425. Min Act: -0.0001

Data Index: 394268 (C4 (Web Text))

Max Activating Token Index: 78

Text #17

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0397. Min Act: -0.0001

Data Index: 173033 (C4 (Web Text))

Max Activating Token Index: 999

Text #18

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0434. Min Act: -0.0001

Data Index: 1317443 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0407. Min Act: -0.0001

Data Index: 102232 (C4 (Web Text))

Max Activating Token Index: 165