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

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

Neuron 5662 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3707. Min Range: -1.3707

Max Act: 1.3495. Min Act: -0.0000

Data Index: 561405 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 1.3707. Min Range: -1.3707

Max Act: 1.3707. Min Act: -0.0000

Data Index: 789923 (C4 (Web Text))

Max Activating Token Index: 963

Text #2

Max Range: 1.3707. Min Range: -1.3707

Max Act: 1.1278. Min Act: -0.0000

Data Index: 1288205 (C4 (Web Text))

Max Activating Token Index: 703

Text #3

Max Range: 1.3707. Min Range: -1.3707

Max Act: 1.1260. Min Act: -0.0000

Data Index: 850592 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 1.3707. Min Range: -1.3707

Max Act: 1.1098. Min Act: -0.0000

Data Index: 174784 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 1.3707. Min Range: -1.3707

Max Act: 1.1238. Min Act: -0.0000

Data Index: 1160552 (C4 (Web Text))

Max Activating Token Index: 585

Text #6

Max Range: 1.3707. Min Range: -1.3707

Max Act: 1.0619. Min Act: -0.0000

Data Index: 31290 (C4 (Web Text))

Max Activating Token Index: 61

Text #7

Max Range: 1.3707. Min Range: -1.3707

Max Act: 1.0865. Min Act: -0.0000

Data Index: 217830 (C4 (Web Text))

Max Activating Token Index: 648

Text #8

Max Range: 1.3707. Min Range: -1.3707

Max Act: 1.0989. Min Act: -0.0000

Data Index: 1197815 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 1.3707. Min Range: -1.3707

Max Act: 1.0581. Min Act: -0.0000

Data Index: 686403 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 1.3707. Min Range: -1.3707

Max Act: 1.0457. Min Act: -0.0000

Data Index: 1271060 (C4 (Web Text))

Max Activating Token Index: 606

Text #11

Max Range: 1.3707. Min Range: -1.3707

Max Act: 1.0427. Min Act: -0.0000

Data Index: 1062211 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 1.3707. Min Range: -1.3707

Max Act: 1.0745. Min Act: -0.0000

Data Index: 187821 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 1.3707. Min Range: -1.3707

Max Act: 1.0023. Min Act: -0.0000

Data Index: 369416 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 1.3707. Min Range: -1.3707

Max Act: 0.9747. Min Act: -0.0000

Data Index: 798930 (C4 (Web Text))

Max Activating Token Index: 360

Text #15

Max Range: 1.3707. Min Range: -1.3707

Max Act: 1.0061. Min Act: -0.0000

Data Index: 1133624 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 1.3707. Min Range: -1.3707

Max Act: 1.0013. Min Act: -0.0000

Data Index: 21259 (C4 (Web Text))

Max Activating Token Index: 564

Text #17

Max Range: 1.3707. Min Range: -1.3707

Max Act: 0.9855. Min Act: -0.0000

Data Index: 1170439 (C4 (Web Text))

Max Activating Token Index: 694

Text #18

Max Range: 1.3707. Min Range: -1.3707

Max Act: 0.9917. Min Act: -0.0000

Data Index: 845583 (C4 (Web Text))

Max Activating Token Index: 172

Text #19

Max Range: 1.3707. Min Range: -1.3707

Max Act: 0.9767. Min Act: -0.0000

Data Index: 804309 (C4 (Web Text))

Max Activating Token Index: 553