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

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

Neuron 237 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2168. Min Range: -2.2168

Max Act: 2.1189. Min Act: -0.0000

Data Index: 1489162 (Python Code)

Max Activating Token Index: 725

Text #1

Max Range: 2.2168. Min Range: -2.2168

Max Act: 2.2168. Min Act: 0.0000

Data Index: 1568239 (Python Code)

Max Activating Token Index: 800

Text #2

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.9126. Min Act: -0.0000

Data Index: 1647787 (Python Code)

Max Activating Token Index: 476

Text #3

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.9651. Min Act: 0.0000

Data Index: 1528888 (Python Code)

Max Activating Token Index: 80

Text #4

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.9601. Min Act: 0.0002

Data Index: 1423538 (Python Code)

Max Activating Token Index: 184

Text #5

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.8424. Min Act: -0.0000

Data Index: 1634286 (Python Code)

Max Activating Token Index: 380

Text #6

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.8796. Min Act: 0.0001

Data Index: 1475392 (Python Code)

Max Activating Token Index: 788

Text #7

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.8011. Min Act: 0.0000

Data Index: 1599387 (Python Code)

Max Activating Token Index: 293

Text #8

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.8261. Min Act: -0.0000

Data Index: 1654219 (Python Code)

Max Activating Token Index: 122

Text #9

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.7645. Min Act: 0.0000

Data Index: 1530528 (Python Code)

Max Activating Token Index: 379

Text #10

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.8027. Min Act: -0.0000

Data Index: 1414979 (Python Code)

Max Activating Token Index: 866

Text #11

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.8800. Min Act: -0.0000

Data Index: 1645538 (Python Code)

Max Activating Token Index: 184

Text #12

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.8359. Min Act: 0.0001

Data Index: 1622102 (Python Code)

Max Activating Token Index: 419

Text #13

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.7267. Min Act: -0.0000

Data Index: 1488240 (Python Code)

Max Activating Token Index: 858

Text #14

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.7415. Min Act: 0.0001

Data Index: 1523086 (Python Code)

Max Activating Token Index: 605

Text #15

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.6179. Min Act: 0.0000

Data Index: 1445498 (Python Code)

Max Activating Token Index: 229

Text #16

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.5951. Min Act: 0.0000

Data Index: 1404490 (Python Code)

Max Activating Token Index: 59

Text #17

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.6359. Min Act: -0.0000

Data Index: 1555457 (Python Code)

Max Activating Token Index: 111

Text #18

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.5758. Min Act: -0.0000

Data Index: 1386586 (Python Code)

Max Activating Token Index: 986

Text #19

Max Range: 2.2168. Min Range: -2.2168

Max Act: 1.6212. Min Act: 0.0000

Data Index: 1361589 (Python Code)

Max Activating Token Index: 553