Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5784 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.4480. Min Range: -2.4480

Max Act: 2.4480. Min Act: -0.0000

Data Index: 1433329 (Python Code)

Max Activating Token Index: 232

Text #1

Max Range: 2.4480. Min Range: -2.4480

Max Act: 2.3600. Min Act: -0.0000

Data Index: 1414798 (Python Code)

Max Activating Token Index: 8

Text #2

Max Range: 2.4480. Min Range: -2.4480

Max Act: 2.1814. Min Act: -0.0000

Data Index: 1505275 (Python Code)

Max Activating Token Index: 450

Text #3

Max Range: 2.4480. Min Range: -2.4480

Max Act: 1.9938. Min Act: -0.0000

Data Index: 1537253 (Python Code)

Max Activating Token Index: 561

Text #4

Max Range: 2.4480. Min Range: -2.4480

Max Act: 2.2910. Min Act: -0.0000

Data Index: 1383655 (Python Code)

Max Activating Token Index: 987

Text #5

Max Range: 2.4480. Min Range: -2.4480

Max Act: 1.9910. Min Act: -0.0000

Data Index: 1364999 (Python Code)

Max Activating Token Index: 12

Text #6

Max Range: 2.4480. Min Range: -2.4480

Max Act: 1.9779. Min Act: -0.0000

Data Index: 1608547 (Python Code)

Max Activating Token Index: 928

Text #7

Max Range: 2.4480. Min Range: -2.4480

Max Act: 2.0692. Min Act: -0.0000

Data Index: 1398963 (Python Code)

Max Activating Token Index: 472

Text #8

Max Range: 2.4480. Min Range: -2.4480

Max Act: 1.9687. Min Act: -0.0000

Data Index: 1479003 (Python Code)

Max Activating Token Index: 565

Text #9

Max Range: 2.4480. Min Range: -2.4480

Max Act: 1.9338. Min Act: -0.0000

Data Index: 1468555 (Python Code)

Max Activating Token Index: 826

Text #10

Max Range: 2.4480. Min Range: -2.4480

Max Act: 2.0531. Min Act: -0.0000

Data Index: 1486484 (Python Code)

Max Activating Token Index: 580

Text #11

Max Range: 2.4480. Min Range: -2.4480

Max Act: 1.9456. Min Act: -0.0000

Data Index: 1619676 (Python Code)

Max Activating Token Index: 961

Text #12

Max Range: 2.4480. Min Range: -2.4480

Max Act: 1.9294. Min Act: -0.0000

Data Index: 1412112 (Python Code)

Max Activating Token Index: 156

Text #13

Max Range: 2.4480. Min Range: -2.4480

Max Act: 1.9164. Min Act: -0.0000

Data Index: 1508103 (Python Code)

Max Activating Token Index: 316

Text #14

Max Range: 2.4480. Min Range: -2.4480

Max Act: 1.8772. Min Act: -0.0000

Data Index: 1651070 (Python Code)

Max Activating Token Index: 2

Text #15

Max Range: 2.4480. Min Range: -2.4480

Max Act: 1.8772. Min Act: -0.0000

Data Index: 1461022 (Python Code)

Max Activating Token Index: 2

Text #16

Max Range: 2.4480. Min Range: -2.4480

Max Act: 1.8561. Min Act: -0.0000

Data Index: 1439363 (Python Code)

Max Activating Token Index: 328

Text #17

Max Range: 2.4480. Min Range: -2.4480

Max Act: 1.7411. Min Act: -0.0000

Data Index: 1459980 (Python Code)

Max Activating Token Index: 635

Text #18

Max Range: 2.4480. Min Range: -2.4480

Max Act: 1.6421. Min Act: -0.0000

Data Index: 1472670 (Python Code)

Max Activating Token Index: 373

Text #19

Max Range: 2.4480. Min Range: -2.4480

Max Act: 1.9214. Min Act: -0.0000

Data Index: 1555302 (Python Code)

Max Activating Token Index: 261