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

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

Neuron 5889 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.6968. Min Act: -0.0001

Data Index: 1383071 (Python Code)

Max Activating Token Index: 142

Text #1

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.4794. Min Act: -0.0000

Data Index: 1390695 (Python Code)

Max Activating Token Index: 398

Text #2

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.6721. Min Act: -0.0000

Data Index: 1364497 (Python Code)

Max Activating Token Index: 571

Text #3

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.6226. Min Act: -0.0001

Data Index: 1518526 (Python Code)

Max Activating Token Index: 8

Text #4

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.5106. Min Act: -0.0001

Data Index: 1544919 (Python Code)

Max Activating Token Index: 29

Text #5

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.5731. Min Act: -0.0001

Data Index: 1606233 (Python Code)

Max Activating Token Index: 5

Text #6

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.6389. Min Act: -0.0001

Data Index: 1501869 (Python Code)

Max Activating Token Index: 59

Text #7

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.5491. Min Act: -0.0000

Data Index: 1584508 (Python Code)

Max Activating Token Index: 6

Text #8

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.4613. Min Act: -0.0000

Data Index: 1645075 (Python Code)

Max Activating Token Index: 5

Text #9

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.6293. Min Act: -0.0001

Data Index: 1373100 (Python Code)

Max Activating Token Index: 8

Text #10

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.4221. Min Act: -0.0001

Data Index: 1417919 (Python Code)

Max Activating Token Index: 241

Text #11

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.4758. Min Act: -0.0000

Data Index: 1529599 (Python Code)

Max Activating Token Index: 7

Text #12

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.3834. Min Act: -0.0001

Data Index: 1438309 (Python Code)

Max Activating Token Index: 877

Text #13

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.4639. Min Act: -0.0000

Data Index: 1456954 (Python Code)

Max Activating Token Index: 13

Text #14

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.4948. Min Act: -0.0001

Data Index: 1490786 (Python Code)

Max Activating Token Index: 34

Text #15

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.4367. Min Act: -0.0001

Data Index: 1595873 (Python Code)

Max Activating Token Index: 326

Text #16

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.4443. Min Act: -0.0001

Data Index: 1405523 (Python Code)

Max Activating Token Index: 15

Text #17

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.3994. Min Act: -0.0000

Data Index: 1495726 (Python Code)

Max Activating Token Index: 4

Text #18

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.3826. Min Act: -0.0000

Data Index: 1619983 (Python Code)

Max Activating Token Index: 318

Text #19

Max Range: 1.6968. Min Range: -1.6968

Max Act: 1.3773. Min Act: -0.0001

Data Index: 1427026 (Python Code)

Max Activating Token Index: 476