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

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

Neuron 2931 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.7495. Min Act: -0.0000

Data Index: 1602331 (Python Code)

Max Activating Token Index: 961

Text #1

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5891. Min Act: -0.0000

Data Index: 1402077 (Python Code)

Max Activating Token Index: 966

Text #2

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5766. Min Act: -0.0000

Data Index: 1655652 (Python Code)

Max Activating Token Index: 784

Text #3

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5662. Min Act: -0.0000

Data Index: 1522514 (Python Code)

Max Activating Token Index: 253

Text #4

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5875. Min Act: -0.0000

Data Index: 1625041 (Python Code)

Max Activating Token Index: 927

Text #5

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.6522. Min Act: -0.0000

Data Index: 434672 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.4788. Min Act: -0.0000

Data Index: 1393959 (Python Code)

Max Activating Token Index: 845

Text #7

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5282. Min Act: -0.0000

Data Index: 1605562 (Python Code)

Max Activating Token Index: 718

Text #8

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5797. Min Act: -0.0000

Data Index: 1367577 (Python Code)

Max Activating Token Index: 700

Text #9

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.6117. Min Act: -0.0000

Data Index: 1522688 (Python Code)

Max Activating Token Index: 446

Text #10

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5132. Min Act: -0.0000

Data Index: 1646800 (Python Code)

Max Activating Token Index: 797

Text #11

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.4926. Min Act: -0.0000

Data Index: 1591614 (Python Code)

Max Activating Token Index: 295

Text #12

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5564. Min Act: -0.0000

Data Index: 1444595 (Python Code)

Max Activating Token Index: 973

Text #13

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5159. Min Act: -0.0000

Data Index: 1568044 (Python Code)

Max Activating Token Index: 821

Text #14

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.6000. Min Act: -0.0000

Data Index: 1649214 (Python Code)

Max Activating Token Index: 306

Text #15

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5010. Min Act: -0.0000

Data Index: 1548812 (Python Code)

Max Activating Token Index: 94

Text #16

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.4991. Min Act: -0.0000

Data Index: 316079 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5016. Min Act: -0.0000

Data Index: 384599 (C4 (Web Text))

Max Activating Token Index: 180

Text #18

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.4651. Min Act: -0.0000

Data Index: 1237323 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.4926. Min Act: -0.0000

Data Index: 680144 (C4 (Web Text))

Max Activating Token Index: 246