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

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

Neuron 52 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: 3.3750. Min Range: -3.3750

Max Act: 3.3750. Min Act: -0.0000

Data Index: 1518063 (Python Code)

Max Activating Token Index: 670

Text #1

Max Range: 3.3750. Min Range: -3.3750

Max Act: 2.7531. Min Act: -0.0000

Data Index: 1403207 (Python Code)

Max Activating Token Index: 994

Text #2

Max Range: 3.3750. Min Range: -3.3750

Max Act: 3.0398. Min Act: -0.0000

Data Index: 1533685 (Python Code)

Max Activating Token Index: 27

Text #3

Max Range: 3.3750. Min Range: -3.3750

Max Act: 2.8292. Min Act: -0.0000

Data Index: 1574166 (Python Code)

Max Activating Token Index: 43

Text #4

Max Range: 3.3750. Min Range: -3.3750

Max Act: 2.3112. Min Act: -0.0000

Data Index: 1462495 (Python Code)

Max Activating Token Index: 192

Text #5

Max Range: 3.3750. Min Range: -3.3750

Max Act: 1.8637. Min Act: -0.0000

Data Index: 1503520 (Python Code)

Max Activating Token Index: 972

Text #6

Max Range: 3.3750. Min Range: -3.3750

Max Act: 2.0024. Min Act: -0.0000

Data Index: 1596711 (Python Code)

Max Activating Token Index: 891

Text #7

Max Range: 3.3750. Min Range: -3.3750

Max Act: 1.8702. Min Act: -0.0000

Data Index: 1388860 (Python Code)

Max Activating Token Index: 138

Text #8

Max Range: 3.3750. Min Range: -3.3750

Max Act: 1.9406. Min Act: -0.0000

Data Index: 1432313 (Python Code)

Max Activating Token Index: 49

Text #9

Max Range: 3.3750. Min Range: -3.3750

Max Act: 1.6255. Min Act: -0.0000

Data Index: 1534895 (Python Code)

Max Activating Token Index: 557

Text #10

Max Range: 3.3750. Min Range: -3.3750

Max Act: 1.6325. Min Act: -0.0000

Data Index: 1429375 (Python Code)

Max Activating Token Index: 1021

Text #11

Max Range: 3.3750. Min Range: -3.3750

Max Act: 1.6389. Min Act: -0.0000

Data Index: 1528255 (Python Code)

Max Activating Token Index: 847

Text #12

Max Range: 3.3750. Min Range: -3.3750

Max Act: 1.6411. Min Act: -0.0000

Data Index: 1366815 (Python Code)

Max Activating Token Index: 961

Text #13

Max Range: 3.3750. Min Range: -3.3750

Max Act: 1.6462. Min Act: -0.0000

Data Index: 1488553 (Python Code)

Max Activating Token Index: 549

Text #14

Max Range: 3.3750. Min Range: -3.3750

Max Act: 1.5769. Min Act: -0.0000

Data Index: 310275 (C4 (Web Text))

Max Activating Token Index: 493

Text #15

Max Range: 3.3750. Min Range: -3.3750

Max Act: 1.7934. Min Act: -0.0000

Data Index: 1511043 (Python Code)

Max Activating Token Index: 179

Text #16

Max Range: 3.3750. Min Range: -3.3750

Max Act: 1.4989. Min Act: -0.0000

Data Index: 1639052 (Python Code)

Max Activating Token Index: 432

Text #17

Max Range: 3.3750. Min Range: -3.3750

Max Act: 1.4678. Min Act: -0.0000

Data Index: 1446643 (Python Code)

Max Activating Token Index: 853

Text #18

Max Range: 3.3750. Min Range: -3.3750

Max Act: 1.3532. Min Act: -0.0000

Data Index: 1618634 (Python Code)

Max Activating Token Index: 992

Text #19

Max Range: 3.3750. Min Range: -3.3750

Max Act: 1.4648. Min Act: -0.0000

Data Index: 1379112 (Python Code)

Max Activating Token Index: 890