Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3328 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0562. Min Act: -0.0003

Data Index: 646321 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0561. Min Act: -0.0003

Data Index: 146156 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0558. Min Act: -0.0003

Data Index: 1290382 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0544. Min Act: -0.0003

Data Index: 1296434 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0506. Min Act: -0.0003

Data Index: 664771 (C4 (Web Text))

Max Activating Token Index: 141

Text #5

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0482. Min Act: -0.0003

Data Index: 530132 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0478. Min Act: -0.0003

Data Index: 569828 (C4 (Web Text))

Max Activating Token Index: 185

Text #7

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0483. Min Act: -0.0002

Data Index: 304432 (C4 (Web Text))

Max Activating Token Index: 475

Text #8

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0479. Min Act: -0.0003

Data Index: 1583065 (Python Code)

Max Activating Token Index: 567

Text #9

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0501. Min Act: -0.0002

Data Index: 292835 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0492. Min Act: -0.0002

Data Index: 772228 (C4 (Web Text))

Max Activating Token Index: 429

Text #11

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0480. Min Act: -0.0003

Data Index: 1429666 (Python Code)

Max Activating Token Index: 508

Text #12

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0459. Min Act: -0.0003

Data Index: 310295 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0469. Min Act: -0.0003

Data Index: 471368 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0505. Min Act: -0.0003

Data Index: 732950 (C4 (Web Text))

Max Activating Token Index: 189

Text #15

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0478. Min Act: -0.0003

Data Index: 1231207 (C4 (Web Text))

Max Activating Token Index: 458

Text #16

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0418. Min Act: -0.0003

Data Index: 388753 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0476. Min Act: -0.0003

Data Index: 1324197 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0442. Min Act: -0.0003

Data Index: 446490 (C4 (Web Text))

Max Activating Token Index: 657

Text #19

Max Range: 0.0562. Min Range: -0.0562

Max Act: 0.0471. Min Act: -0.0003

Data Index: 888573 (C4 (Web Text))

Max Activating Token Index: 276