Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 359 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.3614. Min Act: -0.0002

Data Index: 1428833 (Python Code)

Max Activating Token Index: 552

Text #1

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.3387. Min Act: -0.0002

Data Index: 1493438 (Python Code)

Max Activating Token Index: 860

Text #2

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.3179. Min Act: -0.0002

Data Index: 1374286 (Python Code)

Max Activating Token Index: 772

Text #3

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.3160. Min Act: -0.0002

Data Index: 1466244 (Python Code)

Max Activating Token Index: 34

Text #4

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.3062. Min Act: -0.0002

Data Index: 1579576 (Python Code)

Max Activating Token Index: 300

Text #5

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.3062. Min Act: -0.0002

Data Index: 1425535 (Python Code)

Max Activating Token Index: 642

Text #6

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.3036. Min Act: -0.0002

Data Index: 1579914 (Python Code)

Max Activating Token Index: 701

Text #7

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.3008. Min Act: -0.0002

Data Index: 1447966 (Python Code)

Max Activating Token Index: 492

Text #8

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2860. Min Act: -0.0002

Data Index: 1533499 (Python Code)

Max Activating Token Index: 809

Text #9

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2997. Min Act: -0.0002

Data Index: 1636365 (Python Code)

Max Activating Token Index: 580

Text #10

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2935. Min Act: -0.0002

Data Index: 1573738 (Python Code)

Max Activating Token Index: 57

Text #11

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2966. Min Act: -0.0002

Data Index: 1483483 (Python Code)

Max Activating Token Index: 675

Text #12

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2981. Min Act: -0.0003

Data Index: 1582541 (Python Code)

Max Activating Token Index: 602

Text #13

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2892. Min Act: -0.0002

Data Index: 1640276 (Python Code)

Max Activating Token Index: 792

Text #14

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2989. Min Act: -0.0002

Data Index: 1486838 (Python Code)

Max Activating Token Index: 619

Text #15

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2903. Min Act: -0.0002

Data Index: 1526045 (Python Code)

Max Activating Token Index: 918

Text #16

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2789. Min Act: -0.0002

Data Index: 1628831 (Python Code)

Max Activating Token Index: 998

Text #17

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2807. Min Act: -0.0002

Data Index: 947039 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2719. Min Act: -0.0002

Data Index: 1648465 (Python Code)

Max Activating Token Index: 932

Text #19

Max Range: 0.3614. Min Range: -0.3614

Max Act: 0.2727. Min Act: -0.0002

Data Index: 1436442 (Python Code)

Max Activating Token Index: 577