Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1594 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0618. Min Act: -0.0006

Data Index: 636092 (C4 (Web Text))

Max Activating Token Index: 694

Text #1

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0664. Min Act: -0.0006

Data Index: 193788 (C4 (Web Text))

Max Activating Token Index: 292

Text #2

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0655. Min Act: -0.0006

Data Index: 906019 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0640. Min Act: -0.0006

Data Index: 620227 (C4 (Web Text))

Max Activating Token Index: 647

Text #4

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0604. Min Act: -0.0005

Data Index: 155387 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0633. Min Act: -0.0006

Data Index: 1171916 (C4 (Web Text))

Max Activating Token Index: 988

Text #6

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0602. Min Act: -0.0006

Data Index: 796493 (C4 (Web Text))

Max Activating Token Index: 357

Text #7

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0605. Min Act: -0.0006

Data Index: 41208 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0609. Min Act: -0.0006

Data Index: 544442 (C4 (Web Text))

Max Activating Token Index: 739

Text #9

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0599. Min Act: -0.0006

Data Index: 275562 (C4 (Web Text))

Max Activating Token Index: 512

Text #10

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0606. Min Act: -0.0006

Data Index: 528381 (C4 (Web Text))

Max Activating Token Index: 293

Text #11

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0591. Min Act: -0.0006

Data Index: 935511 (C4 (Web Text))

Max Activating Token Index: 254

Text #12

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0603. Min Act: -0.0006

Data Index: 944483 (C4 (Web Text))

Max Activating Token Index: 271

Text #13

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0563. Min Act: -0.0005

Data Index: 659294 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0583. Min Act: -0.0006

Data Index: 1049060 (C4 (Web Text))

Max Activating Token Index: 338

Text #15

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0571. Min Act: -0.0006

Data Index: 233717 (C4 (Web Text))

Max Activating Token Index: 65

Text #16

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0582. Min Act: -0.0006

Data Index: 42371 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0569. Min Act: -0.0005

Data Index: 695008 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0555. Min Act: -0.0006

Data Index: 708093 (C4 (Web Text))

Max Activating Token Index: 276

Text #19

Max Range: 0.0664. Min Range: -0.0664

Max Act: 0.0577. Min Act: -0.0006

Data Index: 1195949 (C4 (Web Text))

Max Activating Token Index: 57