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

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

Neuron 2895 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: 0.2083. Min Range: -0.2083

Max Act: 0.2083. Min Act: -0.0002

Data Index: 1285116 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1847. Min Act: -0.0002

Data Index: 79081 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1822. Min Act: -0.0002

Data Index: 42121 (C4 (Web Text))

Max Activating Token Index: 329

Text #3

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1884. Min Act: -0.0002

Data Index: 797225 (C4 (Web Text))

Max Activating Token Index: 600

Text #4

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1849. Min Act: -0.0002

Data Index: 529049 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1703. Min Act: -0.0002

Data Index: 898693 (C4 (Web Text))

Max Activating Token Index: 882

Text #6

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1681. Min Act: -0.0002

Data Index: 351686 (C4 (Web Text))

Max Activating Token Index: 58

Text #7

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1730. Min Act: -0.0002

Data Index: 913500 (C4 (Web Text))

Max Activating Token Index: 1004

Text #8

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1890. Min Act: -0.0002

Data Index: 51840 (C4 (Web Text))

Max Activating Token Index: 183

Text #9

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1700. Min Act: -0.0002

Data Index: 408242 (C4 (Web Text))

Max Activating Token Index: 731

Text #10

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1437. Min Act: -0.0002

Data Index: 1237141 (C4 (Web Text))

Max Activating Token Index: 237

Text #11

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1428. Min Act: -0.0002

Data Index: 554684 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1689. Min Act: -0.0002

Data Index: 29178 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1415. Min Act: -0.0002

Data Index: 374193 (C4 (Web Text))

Max Activating Token Index: 146

Text #14

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1716. Min Act: -0.0002

Data Index: 315874 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1499. Min Act: -0.0002

Data Index: 362887 (C4 (Web Text))

Max Activating Token Index: 31

Text #16

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1277. Min Act: -0.0002

Data Index: 49874 (C4 (Web Text))

Max Activating Token Index: 602

Text #17

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1487. Min Act: -0.0002

Data Index: 858218 (C4 (Web Text))

Max Activating Token Index: 781

Text #18

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1407. Min Act: -0.0002

Data Index: 353039 (C4 (Web Text))

Max Activating Token Index: 998

Text #19

Max Range: 0.2083. Min Range: -0.2083

Max Act: 0.1687. Min Act: -0.0002

Data Index: 746150 (C4 (Web Text))

Max Activating Token Index: 370