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

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

Neuron 4991 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2973. Min Range: -1.2973

Max Act: 1.2973. Min Act: -0.0000

Data Index: 1537425 (Python Code)

Max Activating Token Index: 503

Text #1

Max Range: 1.2973. Min Range: -1.2973

Max Act: 1.1969. Min Act: -0.0000

Data Index: 1509080 (Python Code)

Max Activating Token Index: 301

Text #2

Max Range: 1.2973. Min Range: -1.2973

Max Act: 1.1581. Min Act: -0.0000

Data Index: 1395018 (Python Code)

Max Activating Token Index: 582

Text #3

Max Range: 1.2973. Min Range: -1.2973

Max Act: 0.9005. Min Act: -0.0000

Data Index: 1559734 (Python Code)

Max Activating Token Index: 827

Text #4

Max Range: 1.2973. Min Range: -1.2973

Max Act: 0.8849. Min Act: -0.0000

Data Index: 1612291 (Python Code)

Max Activating Token Index: 772

Text #5

Max Range: 1.2973. Min Range: -1.2973

Max Act: 0.9365. Min Act: -0.0000

Data Index: 1433954 (Python Code)

Max Activating Token Index: 1021

Text #6

Max Range: 1.2973. Min Range: -1.2973

Max Act: 0.8330. Min Act: -0.0000

Data Index: 1530605 (Python Code)

Max Activating Token Index: 7

Text #7

Max Range: 1.2973. Min Range: -1.2973

Max Act: 0.8467. Min Act: -0.0000

Data Index: 1635049 (Python Code)

Max Activating Token Index: 718

Text #8

Max Range: 1.2973. Min Range: -1.2973

Max Act: 0.8477. Min Act: -0.0000

Data Index: 1587107 (Python Code)

Max Activating Token Index: 351

Text #9

Max Range: 1.2973. Min Range: -1.2973

Max Act: 0.7838. Min Act: -0.0000

Data Index: 1438889 (Python Code)

Max Activating Token Index: 702

Text #10

Max Range: 1.2973. Min Range: -1.2973

Max Act: 0.8265. Min Act: -0.0000

Data Index: 1445057 (Python Code)

Max Activating Token Index: 875

Text #11

Max Range: 1.2973. Min Range: -1.2973

Max Act: 0.7942. Min Act: -0.0000

Data Index: 1510981 (Python Code)

Max Activating Token Index: 685

Text #12

Max Range: 1.2973. Min Range: -1.2973

Max Act: 0.7883. Min Act: -0.0000

Data Index: 1431343 (Python Code)

Max Activating Token Index: 391

Text #13

Max Range: 1.2973. Min Range: -1.2973

Max Act: 0.7990. Min Act: -0.0000

Data Index: 1526577 (Python Code)

Max Activating Token Index: 560

Text #14

Max Range: 1.2973. Min Range: -1.2973

Max Act: 0.8251. Min Act: -0.0000

Data Index: 1448895 (Python Code)

Max Activating Token Index: 251

Text #15

Max Range: 1.2973. Min Range: -1.2973

Max Act: 0.7846. Min Act: -0.0000

Data Index: 1628269 (Python Code)

Max Activating Token Index: 72

Text #16

Max Range: 1.2973. Min Range: -1.2973

Max Act: 0.7284. Min Act: -0.0000

Data Index: 1428617 (Python Code)

Max Activating Token Index: 277

Text #17

Max Range: 1.2973. Min Range: -1.2973

Max Act: 0.7760. Min Act: -0.0000

Data Index: 1519322 (Python Code)

Max Activating Token Index: 703

Text #18

Max Range: 1.2973. Min Range: -1.2973

Max Act: 0.7027. Min Act: -0.0000

Data Index: 1421430 (Python Code)

Max Activating Token Index: 453

Text #19

Max Range: 1.2973. Min Range: -1.2973

Max Act: 0.7736. Min Act: -0.0000

Data Index: 1366507 (Python Code)

Max Activating Token Index: 663