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

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

Neuron 25 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: 0.3654. Min Range: -0.3654

Max Act: 0.3580. Min Act: -0.0002

Data Index: 316416 (C4 (Web Text))

Max Activating Token Index: 246

Text #1

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3597. Min Act: -0.0002

Data Index: 604392 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3518. Min Act: -0.0002

Data Index: 295276 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3424. Min Act: -0.0002

Data Index: 1228392 (C4 (Web Text))

Max Activating Token Index: 315

Text #4

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3654. Min Act: -0.0002

Data Index: 1217027 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3629. Min Act: -0.0002

Data Index: 910689 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3588. Min Act: -0.0002

Data Index: 681086 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3472. Min Act: -0.0002

Data Index: 106288 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3585. Min Act: -0.0002

Data Index: 1203551 (C4 (Web Text))

Max Activating Token Index: 374

Text #9

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3452. Min Act: -0.0002

Data Index: 547275 (C4 (Web Text))

Max Activating Token Index: 522

Text #10

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3429. Min Act: -0.0002

Data Index: 229343 (C4 (Web Text))

Max Activating Token Index: 481

Text #11

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3506. Min Act: -0.0002

Data Index: 18585 (C4 (Web Text))

Max Activating Token Index: 278

Text #12

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3524. Min Act: -0.0002

Data Index: 333281 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3529. Min Act: -0.0002

Data Index: 1063999 (C4 (Web Text))

Max Activating Token Index: 940

Text #14

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3507. Min Act: -0.0002

Data Index: 1134732 (C4 (Web Text))

Max Activating Token Index: 1005

Text #15

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3308. Min Act: -0.0002

Data Index: 735556 (C4 (Web Text))

Max Activating Token Index: 205

Text #16

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3373. Min Act: -0.0002

Data Index: 1116860 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3452. Min Act: -0.0002

Data Index: 1166646 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3298. Min Act: -0.0002

Data Index: 1346713 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 0.3654. Min Range: -0.3654

Max Act: 0.3523. Min Act: -0.0002

Data Index: 1038317 (C4 (Web Text))

Max Activating Token Index: 315