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

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

Neuron 152 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0632. Min Act: -0.0002

Data Index: 260696 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0498. Min Act: -0.0002

Data Index: 101437 (C4 (Web Text))

Max Activating Token Index: 288

Text #2

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0610. Min Act: -0.0002

Data Index: 295488 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0558. Min Act: -0.0002

Data Index: 1424372 (Python Code)

Max Activating Token Index: 288

Text #4

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0584. Min Act: -0.0002

Data Index: 785335 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0556. Min Act: -0.0002

Data Index: 594427 (C4 (Web Text))

Max Activating Token Index: 479

Text #6

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0536. Min Act: -0.0002

Data Index: 1592266 (Python Code)

Max Activating Token Index: 603

Text #7

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0549. Min Act: -0.0002

Data Index: 1440597 (Python Code)

Max Activating Token Index: 636

Text #8

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0588. Min Act: -0.0002

Data Index: 863191 (C4 (Web Text))

Max Activating Token Index: 253

Text #9

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0591. Min Act: -0.0002

Data Index: 1426523 (Python Code)

Max Activating Token Index: 252

Text #10

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0539. Min Act: -0.0002

Data Index: 1426723 (Python Code)

Max Activating Token Index: 802

Text #11

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0538. Min Act: -0.0002

Data Index: 1400169 (Python Code)

Max Activating Token Index: 676

Text #12

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0561. Min Act: -0.0002

Data Index: 953354 (C4 (Web Text))

Max Activating Token Index: 466

Text #13

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0541. Min Act: -0.0002

Data Index: 109584 (C4 (Web Text))

Max Activating Token Index: 921

Text #14

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0562. Min Act: -0.0002

Data Index: 1436136 (Python Code)

Max Activating Token Index: 587

Text #15

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0531. Min Act: -0.0002

Data Index: 1607011 (Python Code)

Max Activating Token Index: 264

Text #16

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0552. Min Act: -0.0002

Data Index: 425055 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0662. Min Act: -0.0002

Data Index: 669552 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0527. Min Act: -0.0002

Data Index: 294526 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 0.0662. Min Range: -0.0662

Max Act: 0.0528. Min Act: -0.0002

Data Index: 32668 (C4 (Web Text))

Max Activating Token Index: 733