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

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

Neuron 3418 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.2046. Min Act: -0.0000

Data Index: 780648 (C4 (Web Text))

Max Activating Token Index: 590

Text #1

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1670. Min Act: -0.0000

Data Index: 755820 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1985. Min Act: -0.0000

Data Index: 1007049 (C4 (Web Text))

Max Activating Token Index: 769

Text #3

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1701. Min Act: -0.0000

Data Index: 517880 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1702. Min Act: -0.0000

Data Index: 206755 (C4 (Web Text))

Max Activating Token Index: 256

Text #5

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1475. Min Act: -0.0000

Data Index: 1231795 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1581. Min Act: -0.0000

Data Index: 946342 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1515. Min Act: -0.0000

Data Index: 614212 (C4 (Web Text))

Max Activating Token Index: 555

Text #8

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1560. Min Act: -0.0000

Data Index: 18646 (C4 (Web Text))

Max Activating Token Index: 824

Text #9

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1445. Min Act: -0.0000

Data Index: 1203999 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1508. Min Act: -0.0000

Data Index: 128314 (C4 (Web Text))

Max Activating Token Index: 263

Text #11

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1438. Min Act: -0.0000

Data Index: 1513816 (Python Code)

Max Activating Token Index: 857

Text #12

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1502. Min Act: -0.0000

Data Index: 444965 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1368. Min Act: -0.0000

Data Index: 869891 (C4 (Web Text))

Max Activating Token Index: 925

Text #14

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1236. Min Act: -0.0000

Data Index: 584960 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1404. Min Act: -0.0000

Data Index: 705242 (C4 (Web Text))

Max Activating Token Index: 628

Text #16

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1255. Min Act: -0.0000

Data Index: 1420444 (Python Code)

Max Activating Token Index: 834

Text #17

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1193. Min Act: -0.0000

Data Index: 1594551 (Python Code)

Max Activating Token Index: 651

Text #18

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1172. Min Act: -0.0000

Data Index: 817708 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 0.2046. Min Range: -0.2046

Max Act: 0.1229. Min Act: -0.0000

Data Index: 134086 (C4 (Web Text))

Max Activating Token Index: 555