Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1728 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0593. Min Act: -0.0002

Data Index: 1600266 (Python Code)

Max Activating Token Index: 44

Text #1

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0599. Min Act: -0.0003

Data Index: 1374263 (Python Code)

Max Activating Token Index: 445

Text #2

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0578. Min Act: -0.0003

Data Index: 1650031 (Python Code)

Max Activating Token Index: 806

Text #3

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0575. Min Act: -0.0003

Data Index: 1630061 (Python Code)

Max Activating Token Index: 510

Text #4

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0549. Min Act: -0.0003

Data Index: 1484107 (Python Code)

Max Activating Token Index: 118

Text #5

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0547. Min Act: -0.0003

Data Index: 1493375 (Python Code)

Max Activating Token Index: 744

Text #6

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0553. Min Act: -0.0003

Data Index: 1645703 (Python Code)

Max Activating Token Index: 8

Text #7

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0556. Min Act: -0.0003

Data Index: 1612334 (Python Code)

Max Activating Token Index: 928

Text #8

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0542. Min Act: -0.0003

Data Index: 1534538 (Python Code)

Max Activating Token Index: 628

Text #9

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0534. Min Act: -0.0003

Data Index: 1655982 (Python Code)

Max Activating Token Index: 274

Text #10

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0524. Min Act: -0.0003

Data Index: 655912 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0530. Min Act: -0.0002

Data Index: 1448635 (Python Code)

Max Activating Token Index: 451

Text #12

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0534. Min Act: -0.0003

Data Index: 1557313 (Python Code)

Max Activating Token Index: 206

Text #13

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0508. Min Act: -0.0003

Data Index: 1599370 (Python Code)

Max Activating Token Index: 751

Text #14

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0515. Min Act: -0.0003

Data Index: 1587804 (Python Code)

Max Activating Token Index: 296

Text #15

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0506. Min Act: -0.0003

Data Index: 1553399 (Python Code)

Max Activating Token Index: 674

Text #16

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0514. Min Act: -0.0003

Data Index: 1622331 (Python Code)

Max Activating Token Index: 497

Text #17

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0519. Min Act: -0.0003

Data Index: 1560234 (Python Code)

Max Activating Token Index: 46

Text #18

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0506. Min Act: -0.0003

Data Index: 1582108 (Python Code)

Max Activating Token Index: 161

Text #19

Max Range: 0.0599. Min Range: -0.0599

Max Act: 0.0493. Min Act: -0.0004

Data Index: 544352 (C4 (Web Text))

Max Activating Token Index: 953