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

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

Neuron 4053 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.2712. Min Act: -0.0003

Data Index: 1429393 (Python Code)

Max Activating Token Index: 6

Text #1

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.2662. Min Act: -0.0002

Data Index: 619638 (C4 (Web Text))

Max Activating Token Index: 112

Text #2

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.2635. Min Act: -0.0003

Data Index: 1203054 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.2422. Min Act: -0.0003

Data Index: 568569 (C4 (Web Text))

Max Activating Token Index: 24

Text #4

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.2246. Min Act: -0.0002

Data Index: 1004772 (C4 (Web Text))

Max Activating Token Index: 28

Text #5

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.2308. Min Act: -0.0002

Data Index: 448746 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.2252. Min Act: -0.0002

Data Index: 1370878 (Python Code)

Max Activating Token Index: 12

Text #7

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.2129. Min Act: -0.0002

Data Index: 1626893 (Python Code)

Max Activating Token Index: 399

Text #8

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.1997. Min Act: -0.0002

Data Index: 1638656 (Python Code)

Max Activating Token Index: 695

Text #9

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.1980. Min Act: -0.0002

Data Index: 1174995 (C4 (Web Text))

Max Activating Token Index: 44

Text #10

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.1906. Min Act: -0.0002

Data Index: 1439508 (Python Code)

Max Activating Token Index: 740

Text #11

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.1893. Min Act: -0.0002

Data Index: 1643510 (Python Code)

Max Activating Token Index: 24

Text #12

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.1771. Min Act: -0.0002

Data Index: 1593668 (Python Code)

Max Activating Token Index: 13

Text #13

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.1835. Min Act: -0.0002

Data Index: 1481498 (Python Code)

Max Activating Token Index: 21

Text #14

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.1800. Min Act: -0.0002

Data Index: 1307275 (C4 (Web Text))

Max Activating Token Index: 18

Text #15

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.1746. Min Act: -0.0002

Data Index: 1062119 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.1787. Min Act: -0.0003

Data Index: 1362924 (Python Code)

Max Activating Token Index: 184

Text #17

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.1775. Min Act: -0.0002

Data Index: 1092145 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.1773. Min Act: -0.0002

Data Index: 1129180 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 0.2712. Min Range: -0.2712

Max Act: 0.1856. Min Act: -0.0002

Data Index: 325263 (C4 (Web Text))

Max Activating Token Index: 76