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

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

Neuron 5 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2532. Min Range: -3.2532

Max Act: 3.1664. Min Act: -0.0000

Data Index: 640788 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 3.2532. Min Range: -3.2532

Max Act: 3.1259. Min Act: -0.0000

Data Index: 603553 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 3.2532. Min Range: -3.2532

Max Act: 3.2532. Min Act: -0.0000

Data Index: 1079479 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 3.2532. Min Range: -3.2532

Max Act: 3.1225. Min Act: -0.0000

Data Index: 1088956 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 3.2532. Min Range: -3.2532

Max Act: 2.8061. Min Act: -0.0000

Data Index: 1191471 (C4 (Web Text))

Max Activating Token Index: 852

Text #5

Max Range: 3.2532. Min Range: -3.2532

Max Act: 2.9637. Min Act: -0.0000

Data Index: 993929 (C4 (Web Text))

Max Activating Token Index: 725

Text #6

Max Range: 3.2532. Min Range: -3.2532

Max Act: 2.8949. Min Act: -0.0000

Data Index: 306544 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 3.2532. Min Range: -3.2532

Max Act: 2.8798. Min Act: -0.0000

Data Index: 280780 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 3.2532. Min Range: -3.2532

Max Act: 2.8515. Min Act: -0.0000

Data Index: 1348939 (C4 (Web Text))

Max Activating Token Index: 476

Text #9

Max Range: 3.2532. Min Range: -3.2532

Max Act: 3.1348. Min Act: -0.0000

Data Index: 725591 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 3.2532. Min Range: -3.2532

Max Act: 2.8982. Min Act: -0.0000

Data Index: 841202 (C4 (Web Text))

Max Activating Token Index: 942

Text #11

Max Range: 3.2532. Min Range: -3.2532

Max Act: 2.7456. Min Act: -0.0000

Data Index: 700808 (C4 (Web Text))

Max Activating Token Index: 218

Text #12

Max Range: 3.2532. Min Range: -3.2532

Max Act: 2.8513. Min Act: -0.0000

Data Index: 1093976 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 3.2532. Min Range: -3.2532

Max Act: 2.8499. Min Act: -0.0000

Data Index: 475388 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 3.2532. Min Range: -3.2532

Max Act: 2.8278. Min Act: -0.0000

Data Index: 1325870 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 3.2532. Min Range: -3.2532

Max Act: 2.6756. Min Act: -0.0000

Data Index: 574879 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 3.2532. Min Range: -3.2532

Max Act: 2.6264. Min Act: -0.0000

Data Index: 1261625 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 3.2532. Min Range: -3.2532

Max Act: 2.5988. Min Act: 0.0000

Data Index: 594433 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 3.2532. Min Range: -3.2532

Max Act: 2.5849. Min Act: -0.0000

Data Index: 1207054 (C4 (Web Text))

Max Activating Token Index: 319

Text #19

Max Range: 3.2532. Min Range: -3.2532

Max Act: 2.4215. Min Act: -0.0000

Data Index: 290608 (C4 (Web Text))

Max Activating Token Index: 174