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

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

Neuron 792 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: 0.0433. Min Range: -0.0433

Max Act: 0.0389. Min Act: -0.0001

Data Index: 270227 (C4 (Web Text))

Max Activating Token Index: 84

Text #1

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0336. Min Act: -0.0001

Data Index: 454090 (C4 (Web Text))

Max Activating Token Index: 89

Text #2

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0383. Min Act: -0.0001

Data Index: 874799 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0387. Min Act: -0.0001

Data Index: 68343 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0375. Min Act: -0.0001

Data Index: 856991 (C4 (Web Text))

Max Activating Token Index: 571

Text #5

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0371. Min Act: -0.0001

Data Index: 912285 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0433. Min Act: -0.0001

Data Index: 1348224 (C4 (Web Text))

Max Activating Token Index: 352

Text #7

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0333. Min Act: -0.0001

Data Index: 304094 (C4 (Web Text))

Max Activating Token Index: 372

Text #8

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0387. Min Act: -0.0001

Data Index: 901530 (C4 (Web Text))

Max Activating Token Index: 169

Text #9

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0366. Min Act: -0.0001

Data Index: 435812 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0346. Min Act: -0.0001

Data Index: 647514 (C4 (Web Text))

Max Activating Token Index: 754

Text #11

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0281. Min Act: -0.0001

Data Index: 907848 (C4 (Web Text))

Max Activating Token Index: 590

Text #12

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0310. Min Act: -0.0001

Data Index: 113295 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0355. Min Act: -0.0001

Data Index: 1360693 (Python Code)

Max Activating Token Index: 806

Text #14

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0323. Min Act: -0.0001

Data Index: 1020837 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0300. Min Act: -0.0001

Data Index: 488597 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0343. Min Act: -0.0001

Data Index: 624927 (C4 (Web Text))

Max Activating Token Index: 151

Text #17

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0302. Min Act: -0.0001

Data Index: 847303 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0284. Min Act: -0.0001

Data Index: 339724 (C4 (Web Text))

Max Activating Token Index: 749

Text #19

Max Range: 0.0433. Min Range: -0.0433

Max Act: 0.0326. Min Act: -0.0001

Data Index: 53742 (C4 (Web Text))

Max Activating Token Index: 206