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

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

Neuron 3490 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: 2.6182. Min Range: -2.6182

Max Act: 2.6182. Min Act: 0.0000

Data Index: 1460792 (Python Code)

Max Activating Token Index: 7

Text #1

Max Range: 2.6182. Min Range: -2.6182

Max Act: 2.3725. Min Act: -0.0000

Data Index: 1539274 (Python Code)

Max Activating Token Index: 664

Text #2

Max Range: 2.6182. Min Range: -2.6182

Max Act: 2.2569. Min Act: -0.0000

Data Index: 1418902 (Python Code)

Max Activating Token Index: 26

Text #3

Max Range: 2.6182. Min Range: -2.6182

Max Act: 1.6649. Min Act: -0.0000

Data Index: 1578226 (Python Code)

Max Activating Token Index: 32

Text #4

Max Range: 2.6182. Min Range: -2.6182

Max Act: 1.6163. Min Act: -0.0000

Data Index: 1402967 (Python Code)

Max Activating Token Index: 570

Text #5

Max Range: 2.6182. Min Range: -2.6182

Max Act: 1.5539. Min Act: 0.0001

Data Index: 1606215 (Python Code)

Max Activating Token Index: 15

Text #6

Max Range: 2.6182. Min Range: -2.6182

Max Act: 1.5810. Min Act: -0.0000

Data Index: 1413596 (Python Code)

Max Activating Token Index: 644

Text #7

Max Range: 2.6182. Min Range: -2.6182

Max Act: 1.4860. Min Act: -0.0000

Data Index: 1434607 (Python Code)

Max Activating Token Index: 702

Text #8

Max Range: 2.6182. Min Range: -2.6182

Max Act: 1.4505. Min Act: 0.0000

Data Index: 1620541 (Python Code)

Max Activating Token Index: 497

Text #9

Max Range: 2.6182. Min Range: -2.6182

Max Act: 1.4444. Min Act: 0.0000

Data Index: 1423689 (Python Code)

Max Activating Token Index: 171

Text #10

Max Range: 2.6182. Min Range: -2.6182

Max Act: 1.5104. Min Act: -0.0000

Data Index: 1540709 (Python Code)

Max Activating Token Index: 216

Text #11

Max Range: 2.6182. Min Range: -2.6182

Max Act: 1.4234. Min Act: -0.0000

Data Index: 1495904 (Python Code)

Max Activating Token Index: 390

Text #12

Max Range: 2.6182. Min Range: -2.6182

Max Act: 1.4980. Min Act: -0.0000

Data Index: 1426799 (Python Code)

Max Activating Token Index: 747

Text #13

Max Range: 2.6182. Min Range: -2.6182

Max Act: 1.3644. Min Act: 0.0001

Data Index: 1571965 (Python Code)

Max Activating Token Index: 645

Text #14

Max Range: 2.6182. Min Range: -2.6182

Max Act: 1.3818. Min Act: -0.0000

Data Index: 1472302 (Python Code)

Max Activating Token Index: 1023

Text #15

Max Range: 2.6182. Min Range: -2.6182

Max Act: 1.1928. Min Act: -0.0000

Data Index: 1404242 (Python Code)

Max Activating Token Index: 627

Text #16

Max Range: 2.6182. Min Range: -2.6182

Max Act: 1.3052. Min Act: 0.0002

Data Index: 1650364 (Python Code)

Max Activating Token Index: 338

Text #17

Max Range: 2.6182. Min Range: -2.6182

Max Act: 1.2134. Min Act: -0.0000

Data Index: 1639603 (Python Code)

Max Activating Token Index: 529

Text #18

Max Range: 2.6182. Min Range: -2.6182

Max Act: 1.1768. Min Act: 0.0001

Data Index: 1532677 (Python Code)

Max Activating Token Index: 551

Text #19

Max Range: 2.6182. Min Range: -2.6182

Max Act: 1.1240. Min Act: -0.0000

Data Index: 1385622 (Python Code)

Max Activating Token Index: 617