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

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

Neuron 5969 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1111. Min Range: -3.1111

Max Act: 3.1111. Min Act: -0.0000

Data Index: 1522682 (Python Code)

Max Activating Token Index: 381

Text #1

Max Range: 3.1111. Min Range: -3.1111

Max Act: 2.8830. Min Act: -0.0000

Data Index: 1534951 (Python Code)

Max Activating Token Index: 178

Text #2

Max Range: 3.1111. Min Range: -3.1111

Max Act: 3.1009. Min Act: -0.0000

Data Index: 1537161 (Python Code)

Max Activating Token Index: 863

Text #3

Max Range: 3.1111. Min Range: -3.1111

Max Act: 2.6581. Min Act: -0.0000

Data Index: 1558613 (Python Code)

Max Activating Token Index: 527

Text #4

Max Range: 3.1111. Min Range: -3.1111

Max Act: 2.3938. Min Act: -0.0000

Data Index: 1520203 (Python Code)

Max Activating Token Index: 888

Text #5

Max Range: 3.1111. Min Range: -3.1111

Max Act: 2.5044. Min Act: -0.0000

Data Index: 1505707 (Python Code)

Max Activating Token Index: 409

Text #6

Max Range: 3.1111. Min Range: -3.1111

Max Act: 2.4885. Min Act: -0.0000

Data Index: 1577638 (Python Code)

Max Activating Token Index: 815

Text #7

Max Range: 3.1111. Min Range: -3.1111

Max Act: 2.3276. Min Act: -0.0000

Data Index: 1536615 (Python Code)

Max Activating Token Index: 522

Text #8

Max Range: 3.1111. Min Range: -3.1111

Max Act: 1.9674. Min Act: -0.0000

Data Index: 1613815 (Python Code)

Max Activating Token Index: 124

Text #9

Max Range: 3.1111. Min Range: -3.1111

Max Act: 2.4036. Min Act: -0.0000

Data Index: 1650064 (Python Code)

Max Activating Token Index: 585

Text #10

Max Range: 3.1111. Min Range: -3.1111

Max Act: 2.2697. Min Act: -0.0000

Data Index: 1608199 (Python Code)

Max Activating Token Index: 125

Text #11

Max Range: 3.1111. Min Range: -3.1111

Max Act: 2.2090. Min Act: -0.0000

Data Index: 1650341 (Python Code)

Max Activating Token Index: 480

Text #12

Max Range: 3.1111. Min Range: -3.1111

Max Act: 2.0002. Min Act: -0.0000

Data Index: 1406473 (Python Code)

Max Activating Token Index: 965

Text #13

Max Range: 3.1111. Min Range: -3.1111

Max Act: 2.0144. Min Act: -0.0000

Data Index: 1388770 (Python Code)

Max Activating Token Index: 224

Text #14

Max Range: 3.1111. Min Range: -3.1111

Max Act: 2.0730. Min Act: -0.0000

Data Index: 1449088 (Python Code)

Max Activating Token Index: 688

Text #15

Max Range: 3.1111. Min Range: -3.1111

Max Act: 2.0445. Min Act: -0.0000

Data Index: 1483491 (Python Code)

Max Activating Token Index: 618

Text #16

Max Range: 3.1111. Min Range: -3.1111

Max Act: 1.8029. Min Act: -0.0000

Data Index: 1634206 (Python Code)

Max Activating Token Index: 183

Text #17

Max Range: 3.1111. Min Range: -3.1111

Max Act: 1.8922. Min Act: -0.0000

Data Index: 1604124 (Python Code)

Max Activating Token Index: 94

Text #18

Max Range: 3.1111. Min Range: -3.1111

Max Act: 1.7959. Min Act: -0.0000

Data Index: 1551658 (Python Code)

Max Activating Token Index: 797

Text #19

Max Range: 3.1111. Min Range: -3.1111

Max Act: 1.9659. Min Act: -0.0000

Data Index: 1586483 (Python Code)

Max Activating Token Index: 920