Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3968 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0825. Min Act: -0.0002

Data Index: 1439718 (Python Code)

Max Activating Token Index: 64

Text #1

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0730. Min Act: -0.0002

Data Index: 1398831 (Python Code)

Max Activating Token Index: 957

Text #2

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0810. Min Act: -0.0002

Data Index: 1497358 (Python Code)

Max Activating Token Index: 279

Text #3

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0907. Min Act: -0.0002

Data Index: 1526277 (Python Code)

Max Activating Token Index: 32

Text #4

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0790. Min Act: -0.0002

Data Index: 1419914 (Python Code)

Max Activating Token Index: 191

Text #5

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0801. Min Act: -0.0002

Data Index: 1386620 (Python Code)

Max Activating Token Index: 564

Text #6

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0731. Min Act: -0.0002

Data Index: 1514448 (Python Code)

Max Activating Token Index: 131

Text #7

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0747. Min Act: -0.0002

Data Index: 1439309 (Python Code)

Max Activating Token Index: 127

Text #8

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0732. Min Act: -0.0002

Data Index: 1595521 (Python Code)

Max Activating Token Index: 266

Text #9

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0630. Min Act: -0.0002

Data Index: 1390514 (Python Code)

Max Activating Token Index: 284

Text #10

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0687. Min Act: -0.0002

Data Index: 1431618 (Python Code)

Max Activating Token Index: 23

Text #11

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0661. Min Act: -0.0002

Data Index: 1579842 (Python Code)

Max Activating Token Index: 830

Text #12

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0729. Min Act: -0.0002

Data Index: 1420552 (Python Code)

Max Activating Token Index: 869

Text #13

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0711. Min Act: -0.0002

Data Index: 1399556 (Python Code)

Max Activating Token Index: 91

Text #14

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0683. Min Act: -0.0002

Data Index: 1553738 (Python Code)

Max Activating Token Index: 8

Text #15

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0697. Min Act: -0.0002

Data Index: 1368741 (Python Code)

Max Activating Token Index: 96

Text #16

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0778. Min Act: -0.0002

Data Index: 1493238 (Python Code)

Max Activating Token Index: 278

Text #17

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0641. Min Act: -0.0002

Data Index: 1567981 (Python Code)

Max Activating Token Index: 39

Text #18

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0699. Min Act: -0.0002

Data Index: 1466164 (Python Code)

Max Activating Token Index: 723

Text #19

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0658. Min Act: -0.0002

Data Index: 1628816 (Python Code)

Max Activating Token Index: 970