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

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

Neuron 4726 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: 4.5863. Min Range: -4.5863

Max Act: 4.5863. Min Act: -0.0000

Data Index: 1570924 (Python Code)

Max Activating Token Index: 727

Text #1

Max Range: 4.5863. Min Range: -4.5863

Max Act: 4.4499. Min Act: -0.0000

Data Index: 1450928 (Python Code)

Max Activating Token Index: 119

Text #2

Max Range: 4.5863. Min Range: -4.5863

Max Act: 4.2314. Min Act: -0.0000

Data Index: 1392319 (Python Code)

Max Activating Token Index: 585

Text #3

Max Range: 4.5863. Min Range: -4.5863

Max Act: 4.1926. Min Act: -0.0000

Data Index: 1641826 (Python Code)

Max Activating Token Index: 430

Text #4

Max Range: 4.5863. Min Range: -4.5863

Max Act: 4.1833. Min Act: -0.0000

Data Index: 1575946 (Python Code)

Max Activating Token Index: 653

Text #5

Max Range: 4.5863. Min Range: -4.5863

Max Act: 4.1432. Min Act: -0.0000

Data Index: 1448118 (Python Code)

Max Activating Token Index: 686

Text #6

Max Range: 4.5863. Min Range: -4.5863

Max Act: 3.8987. Min Act: -0.0000

Data Index: 1495556 (Python Code)

Max Activating Token Index: 772

Text #7

Max Range: 4.5863. Min Range: -4.5863

Max Act: 3.8639. Min Act: -0.0000

Data Index: 1631824 (Python Code)

Max Activating Token Index: 539

Text #8

Max Range: 4.5863. Min Range: -4.5863

Max Act: 3.8694. Min Act: -0.0000

Data Index: 1633521 (Python Code)

Max Activating Token Index: 272

Text #9

Max Range: 4.5863. Min Range: -4.5863

Max Act: 3.8830. Min Act: -0.0000

Data Index: 1585244 (Python Code)

Max Activating Token Index: 738

Text #10

Max Range: 4.5863. Min Range: -4.5863

Max Act: 3.8017. Min Act: -0.0000

Data Index: 1379753 (Python Code)

Max Activating Token Index: 322

Text #11

Max Range: 4.5863. Min Range: -4.5863

Max Act: 3.5780. Min Act: -0.0000

Data Index: 1501194 (Python Code)

Max Activating Token Index: 169

Text #12

Max Range: 4.5863. Min Range: -4.5863

Max Act: 3.7535. Min Act: -0.0000

Data Index: 1556074 (Python Code)

Max Activating Token Index: 412

Text #13

Max Range: 4.5863. Min Range: -4.5863

Max Act: 3.5536. Min Act: -0.0000

Data Index: 1478784 (Python Code)

Max Activating Token Index: 952

Text #14

Max Range: 4.5863. Min Range: -4.5863

Max Act: 3.6636. Min Act: -0.0000

Data Index: 1575617 (Python Code)

Max Activating Token Index: 469

Text #15

Max Range: 4.5863. Min Range: -4.5863

Max Act: 3.6360. Min Act: -0.0000

Data Index: 1381761 (Python Code)

Max Activating Token Index: 927

Text #16

Max Range: 4.5863. Min Range: -4.5863

Max Act: 3.6096. Min Act: -0.0000

Data Index: 1590120 (Python Code)

Max Activating Token Index: 815

Text #17

Max Range: 4.5863. Min Range: -4.5863

Max Act: 3.6028. Min Act: -0.0000

Data Index: 1371076 (Python Code)

Max Activating Token Index: 506

Text #18

Max Range: 4.5863. Min Range: -4.5863

Max Act: 3.4510. Min Act: -0.0000

Data Index: 1583608 (Python Code)

Max Activating Token Index: 466

Text #19

Max Range: 4.5863. Min Range: -4.5863

Max Act: 3.5945. Min Act: -0.0000

Data Index: 1638938 (Python Code)

Max Activating Token Index: 18