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

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

Neuron 5915 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0327. Min Act: -0.0002

Data Index: 119550 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0396. Min Act: -0.0002

Data Index: 904134 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0409. Min Act: -0.0002

Data Index: 1127395 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0449. Min Act: -0.0002

Data Index: 1083393 (C4 (Web Text))

Max Activating Token Index: 161

Text #4

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0380. Min Act: -0.0002

Data Index: 1301847 (C4 (Web Text))

Max Activating Token Index: 433

Text #5

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0382. Min Act: -0.0002

Data Index: 465012 (C4 (Web Text))

Max Activating Token Index: 434

Text #6

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0437. Min Act: -0.0002

Data Index: 270933 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0378. Min Act: -0.0002

Data Index: 577519 (C4 (Web Text))

Max Activating Token Index: 694

Text #8

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0433. Min Act: -0.0002

Data Index: 1055350 (C4 (Web Text))

Max Activating Token Index: 563

Text #9

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0455. Min Act: -0.0002

Data Index: 804590 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0405. Min Act: -0.0002

Data Index: 1258196 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0432. Min Act: -0.0002

Data Index: 415562 (C4 (Web Text))

Max Activating Token Index: 413

Text #12

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0398. Min Act: -0.0002

Data Index: 409673 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0388. Min Act: -0.0002

Data Index: 430774 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0401. Min Act: -0.0002

Data Index: 1210463 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0367. Min Act: -0.0002

Data Index: 996222 (C4 (Web Text))

Max Activating Token Index: 679

Text #16

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0392. Min Act: -0.0002

Data Index: 573810 (C4 (Web Text))

Max Activating Token Index: 656

Text #17

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0411. Min Act: -0.0002

Data Index: 471346 (C4 (Web Text))

Max Activating Token Index: 621

Text #18

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0409. Min Act: -0.0002

Data Index: 1215553 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 0.0455. Min Range: -0.0455

Max Act: 0.0374. Min Act: -0.0002

Data Index: 528914 (C4 (Web Text))

Max Activating Token Index: 451