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

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

Neuron 5234 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3623. Min Range: -3.3623

Max Act: 3.3623. Min Act: -0.0000

Data Index: 1499991 (Python Code)

Max Activating Token Index: 97

Text #1

Max Range: 3.3623. Min Range: -3.3623

Max Act: 3.0139. Min Act: -0.0000

Data Index: 1649035 (Python Code)

Max Activating Token Index: 80

Text #2

Max Range: 3.3623. Min Range: -3.3623

Max Act: 2.7225. Min Act: -0.0000

Data Index: 1619249 (Python Code)

Max Activating Token Index: 83

Text #3

Max Range: 3.3623. Min Range: -3.3623

Max Act: 2.2982. Min Act: -0.0000

Data Index: 1466523 (Python Code)

Max Activating Token Index: 218

Text #4

Max Range: 3.3623. Min Range: -3.3623

Max Act: 2.8940. Min Act: -0.0000

Data Index: 1499936 (Python Code)

Max Activating Token Index: 464

Text #5

Max Range: 3.3623. Min Range: -3.3623

Max Act: 2.5115. Min Act: -0.0000

Data Index: 1537421 (Python Code)

Max Activating Token Index: 743

Text #6

Max Range: 3.3623. Min Range: -3.3623

Max Act: 2.4034. Min Act: -0.0000

Data Index: 1388715 (Python Code)

Max Activating Token Index: 73

Text #7

Max Range: 3.3623. Min Range: -3.3623

Max Act: 1.8247. Min Act: -0.0000

Data Index: 1592901 (Python Code)

Max Activating Token Index: 368

Text #8

Max Range: 3.3623. Min Range: -3.3623

Max Act: 1.9834. Min Act: -0.0000

Data Index: 1552619 (Python Code)

Max Activating Token Index: 456

Text #9

Max Range: 3.3623. Min Range: -3.3623

Max Act: 1.6619. Min Act: -0.0000

Data Index: 1406613 (Python Code)

Max Activating Token Index: 336

Text #10

Max Range: 3.3623. Min Range: -3.3623

Max Act: 1.6627. Min Act: -0.0000

Data Index: 1489297 (Python Code)

Max Activating Token Index: 192

Text #11

Max Range: 3.3623. Min Range: -3.3623

Max Act: 1.5355. Min Act: -0.0000

Data Index: 1386674 (Python Code)

Max Activating Token Index: 454

Text #12

Max Range: 3.3623. Min Range: -3.3623

Max Act: 1.8262. Min Act: -0.0000

Data Index: 1379966 (Python Code)

Max Activating Token Index: 275

Text #13

Max Range: 3.3623. Min Range: -3.3623

Max Act: 1.5186. Min Act: -0.0000

Data Index: 1575466 (Python Code)

Max Activating Token Index: 29

Text #14

Max Range: 3.3623. Min Range: -3.3623

Max Act: 1.5936. Min Act: -0.0000

Data Index: 1501806 (Python Code)

Max Activating Token Index: 634

Text #15

Max Range: 3.3623. Min Range: -3.3623

Max Act: 1.5569. Min Act: -0.0000

Data Index: 1465665 (Python Code)

Max Activating Token Index: 292

Text #16

Max Range: 3.3623. Min Range: -3.3623

Max Act: 1.3931. Min Act: -0.0000

Data Index: 1623694 (Python Code)

Max Activating Token Index: 54

Text #17

Max Range: 3.3623. Min Range: -3.3623

Max Act: 1.4589. Min Act: -0.0000

Data Index: 1502472 (Python Code)

Max Activating Token Index: 42

Text #18

Max Range: 3.3623. Min Range: -3.3623

Max Act: 1.5636. Min Act: -0.0000

Data Index: 1609482 (Python Code)

Max Activating Token Index: 182

Text #19

Max Range: 3.3623. Min Range: -3.3623

Max Act: 1.4397. Min Act: -0.0000

Data Index: 1520042 (Python Code)

Max Activating Token Index: 13