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

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

Neuron 1877 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.7637. Min Act: -0.0000

Data Index: 252397 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.8333. Min Act: -0.0000

Data Index: 1389688 (Python Code)

Max Activating Token Index: 413

Text #2

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.7352. Min Act: -0.0000

Data Index: 1491317 (Python Code)

Max Activating Token Index: 408

Text #3

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.7307. Min Act: -0.0000

Data Index: 1393644 (Python Code)

Max Activating Token Index: 688

Text #4

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.7608. Min Act: -0.0000

Data Index: 1402984 (Python Code)

Max Activating Token Index: 972

Text #5

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.6666. Min Act: -0.0000

Data Index: 1633871 (Python Code)

Max Activating Token Index: 695

Text #6

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.6709. Min Act: -0.0000

Data Index: 1488441 (Python Code)

Max Activating Token Index: 537

Text #7

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.6850. Min Act: -0.0000

Data Index: 1609820 (Python Code)

Max Activating Token Index: 226

Text #8

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.5688. Min Act: -0.0000

Data Index: 1036930 (C4 (Web Text))

Max Activating Token Index: 680

Text #9

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.5871. Min Act: -0.0000

Data Index: 1504469 (Python Code)

Max Activating Token Index: 557

Text #10

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.5856. Min Act: -0.0000

Data Index: 1584294 (Python Code)

Max Activating Token Index: 635

Text #11

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.5945. Min Act: -0.0000

Data Index: 1411156 (Python Code)

Max Activating Token Index: 713

Text #12

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.5266. Min Act: -0.0000

Data Index: 1483252 (Python Code)

Max Activating Token Index: 308

Text #13

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.5691. Min Act: -0.0000

Data Index: 1468196 (Python Code)

Max Activating Token Index: 186

Text #14

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.5430. Min Act: -0.0000

Data Index: 1605228 (Python Code)

Max Activating Token Index: 503

Text #15

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.4992. Min Act: -0.0000

Data Index: 1364750 (Python Code)

Max Activating Token Index: 461

Text #16

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.4949. Min Act: -0.0000

Data Index: 965947 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.5691. Min Act: -0.0000

Data Index: 765806 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.5062. Min Act: -0.0000

Data Index: 1581317 (Python Code)

Max Activating Token Index: 296

Text #19

Max Range: 0.8333. Min Range: -0.8333

Max Act: 0.5059. Min Act: -0.0000

Data Index: 11207 (C4 (Web Text))

Max Activating Token Index: 308