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

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

Neuron 2255 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3840. Min Act: -0.0000

Data Index: 1486354 (Python Code)

Max Activating Token Index: 993

Text #1

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3979. Min Act: -0.0000

Data Index: 1572177 (Python Code)

Max Activating Token Index: 822

Text #2

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3863. Min Act: -0.0000

Data Index: 1425233 (Python Code)

Max Activating Token Index: 900

Text #3

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3592. Min Act: -0.0000

Data Index: 1426776 (Python Code)

Max Activating Token Index: 636

Text #4

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3451. Min Act: -0.0000

Data Index: 1646944 (Python Code)

Max Activating Token Index: 719

Text #5

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3243. Min Act: -0.0000

Data Index: 1545137 (Python Code)

Max Activating Token Index: 379

Text #6

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3553. Min Act: -0.0000

Data Index: 1395072 (Python Code)

Max Activating Token Index: 660

Text #7

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3308. Min Act: -0.0000

Data Index: 1445493 (Python Code)

Max Activating Token Index: 944

Text #8

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3129. Min Act: -0.0000

Data Index: 1557998 (Python Code)

Max Activating Token Index: 887

Text #9

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3061. Min Act: -0.0000

Data Index: 1054088 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3270. Min Act: -0.0000

Data Index: 519496 (C4 (Web Text))

Max Activating Token Index: 303

Text #11

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3317. Min Act: -0.0000

Data Index: 1037848 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3075. Min Act: -0.0000

Data Index: 1573217 (Python Code)

Max Activating Token Index: 609

Text #13

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3250. Min Act: -0.0000

Data Index: 1544932 (Python Code)

Max Activating Token Index: 985

Text #14

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3120. Min Act: -0.0000

Data Index: 1622010 (Python Code)

Max Activating Token Index: 811

Text #15

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.3024. Min Act: -0.0000

Data Index: 1261164 (C4 (Web Text))

Max Activating Token Index: 772

Text #16

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.2722. Min Act: -0.0000

Data Index: 1563335 (Python Code)

Max Activating Token Index: 399

Text #17

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.2591. Min Act: -0.0000

Data Index: 593179 (C4 (Web Text))

Max Activating Token Index: 783

Text #18

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.2863. Min Act: -0.0000

Data Index: 1362258 (Python Code)

Max Activating Token Index: 900

Text #19

Max Range: 0.3979. Min Range: -0.3979

Max Act: 0.2863. Min Act: -0.0000

Data Index: 1536475 (Python Code)

Max Activating Token Index: 665