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

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

Neuron 612 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: 2.5853. Min Range: -2.5853

Max Act: 2.5853. Min Act: -0.0000

Data Index: 1640195 (Python Code)

Max Activating Token Index: 880

Text #1

Max Range: 2.5853. Min Range: -2.5853

Max Act: 2.3704. Min Act: -0.0000

Data Index: 1581910 (Python Code)

Max Activating Token Index: 614

Text #2

Max Range: 2.5853. Min Range: -2.5853

Max Act: 2.4329. Min Act: -0.0000

Data Index: 1619840 (Python Code)

Max Activating Token Index: 831

Text #3

Max Range: 2.5853. Min Range: -2.5853

Max Act: 2.1817. Min Act: -0.0000

Data Index: 1603964 (Python Code)

Max Activating Token Index: 56

Text #4

Max Range: 2.5853. Min Range: -2.5853

Max Act: 2.1730. Min Act: -0.0000

Data Index: 1437407 (Python Code)

Max Activating Token Index: 549

Text #5

Max Range: 2.5853. Min Range: -2.5853

Max Act: 1.9588. Min Act: -0.0000

Data Index: 1559727 (Python Code)

Max Activating Token Index: 449

Text #6

Max Range: 2.5853. Min Range: -2.5853

Max Act: 2.0666. Min Act: -0.0000

Data Index: 1589933 (Python Code)

Max Activating Token Index: 89

Text #7

Max Range: 2.5853. Min Range: -2.5853

Max Act: 2.0621. Min Act: -0.0000

Data Index: 1366795 (Python Code)

Max Activating Token Index: 73

Text #8

Max Range: 2.5853. Min Range: -2.5853

Max Act: 2.1551. Min Act: -0.0000

Data Index: 1406260 (Python Code)

Max Activating Token Index: 694

Text #9

Max Range: 2.5853. Min Range: -2.5853

Max Act: 2.0255. Min Act: -0.0000

Data Index: 1454783 (Python Code)

Max Activating Token Index: 949

Text #10

Max Range: 2.5853. Min Range: -2.5853

Max Act: 1.9181. Min Act: -0.0000

Data Index: 1543460 (Python Code)

Max Activating Token Index: 251

Text #11

Max Range: 2.5853. Min Range: -2.5853

Max Act: 2.0323. Min Act: -0.0000

Data Index: 1635552 (Python Code)

Max Activating Token Index: 342

Text #12

Max Range: 2.5853. Min Range: -2.5853

Max Act: 1.9930. Min Act: -0.0000

Data Index: 1637184 (Python Code)

Max Activating Token Index: 410

Text #13

Max Range: 2.5853. Min Range: -2.5853

Max Act: 2.0127. Min Act: -0.0000

Data Index: 1640186 (Python Code)

Max Activating Token Index: 523

Text #14

Max Range: 2.5853. Min Range: -2.5853

Max Act: 1.8845. Min Act: -0.0000

Data Index: 1628439 (Python Code)

Max Activating Token Index: 409

Text #15

Max Range: 2.5853. Min Range: -2.5853

Max Act: 1.7699. Min Act: -0.0000

Data Index: 1540013 (Python Code)

Max Activating Token Index: 611

Text #16

Max Range: 2.5853. Min Range: -2.5853

Max Act: 1.8647. Min Act: -0.0000

Data Index: 1484466 (Python Code)

Max Activating Token Index: 115

Text #17

Max Range: 2.5853. Min Range: -2.5853

Max Act: 1.8609. Min Act: -0.0000

Data Index: 1372105 (Python Code)

Max Activating Token Index: 39

Text #18

Max Range: 2.5853. Min Range: -2.5853

Max Act: 1.8343. Min Act: -0.0000

Data Index: 1443968 (Python Code)

Max Activating Token Index: 558

Text #19

Max Range: 2.5853. Min Range: -2.5853

Max Act: 1.7796. Min Act: -0.0000

Data Index: 1624843 (Python Code)

Max Activating Token Index: 1007