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

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

Neuron 3629 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: 0.0643. Min Range: -0.0643

Max Act: 0.0643. Min Act: -0.0001

Data Index: 924305 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0405. Min Act: -0.0001

Data Index: 664846 (C4 (Web Text))

Max Activating Token Index: 868

Text #2

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0469. Min Act: -0.0001

Data Index: 1236915 (C4 (Web Text))

Max Activating Token Index: 533

Text #3

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0415. Min Act: -0.0001

Data Index: 1423791 (Python Code)

Max Activating Token Index: 247

Text #4

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0397. Min Act: -0.0002

Data Index: 1633156 (Python Code)

Max Activating Token Index: 289

Text #5

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0397. Min Act: -0.0001

Data Index: 518756 (C4 (Web Text))

Max Activating Token Index: 403

Text #6

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0424. Min Act: -0.0001

Data Index: 354177 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0376. Min Act: -0.0001

Data Index: 1375405 (Python Code)

Max Activating Token Index: 728

Text #8

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0412. Min Act: -0.0001

Data Index: 604033 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0409. Min Act: -0.0001

Data Index: 1574806 (Python Code)

Max Activating Token Index: 260

Text #10

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0405. Min Act: -0.0001

Data Index: 1514361 (Python Code)

Max Activating Token Index: 865

Text #11

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0371. Min Act: -0.0001

Data Index: 694793 (C4 (Web Text))

Max Activating Token Index: 946

Text #12

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0367. Min Act: -0.0001

Data Index: 177461 (C4 (Web Text))

Max Activating Token Index: 353

Text #13

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0369. Min Act: -0.0001

Data Index: 977465 (C4 (Web Text))

Max Activating Token Index: 409

Text #14

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0379. Min Act: -0.0001

Data Index: 371194 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0361. Min Act: -0.0001

Data Index: 1296452 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0370. Min Act: -0.0001

Data Index: 480243 (C4 (Web Text))

Max Activating Token Index: 502

Text #17

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0329. Min Act: -0.0001

Data Index: 1291504 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0358. Min Act: -0.0001

Data Index: 394277 (C4 (Web Text))

Max Activating Token Index: 349

Text #19

Max Range: 0.0643. Min Range: -0.0643

Max Act: 0.0355. Min Act: -0.0001

Data Index: 157383 (C4 (Web Text))

Max Activating Token Index: 443