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

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

Neuron 928 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.5544. Min Act: -0.0000

Data Index: 1084891 (C4 (Web Text))

Max Activating Token Index: 784

Text #1

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.5024. Min Act: -0.0000

Data Index: 1252283 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.4515. Min Act: -0.0000

Data Index: 392967 (C4 (Web Text))

Max Activating Token Index: 348

Text #3

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.4344. Min Act: -0.0000

Data Index: 1328931 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.4293. Min Act: -0.0000

Data Index: 1120916 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.4200. Min Act: -0.0000

Data Index: 1475869 (Python Code)

Max Activating Token Index: 695

Text #6

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.4320. Min Act: -0.0000

Data Index: 1179825 (C4 (Web Text))

Max Activating Token Index: 934

Text #7

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.4098. Min Act: -0.0000

Data Index: 1267033 (C4 (Web Text))

Max Activating Token Index: 250

Text #8

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.4205. Min Act: -0.0000

Data Index: 1615958 (Python Code)

Max Activating Token Index: 857

Text #9

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.4152. Min Act: -0.0000

Data Index: 559403 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.3933. Min Act: -0.0000

Data Index: 637650 (C4 (Web Text))

Max Activating Token Index: 452

Text #11

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.4077. Min Act: -0.0000

Data Index: 1592398 (Python Code)

Max Activating Token Index: 221

Text #12

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.3760. Min Act: -0.0000

Data Index: 1395903 (Python Code)

Max Activating Token Index: 367

Text #13

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.3985. Min Act: -0.0000

Data Index: 1591535 (Python Code)

Max Activating Token Index: 548

Text #14

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.3856. Min Act: -0.0000

Data Index: 52747 (C4 (Web Text))

Max Activating Token Index: 835

Text #15

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.3963. Min Act: -0.0000

Data Index: 1641358 (Python Code)

Max Activating Token Index: 163

Text #16

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.3896. Min Act: -0.0000

Data Index: 820936 (C4 (Web Text))

Max Activating Token Index: 710

Text #17

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.3747. Min Act: -0.0000

Data Index: 699824 (C4 (Web Text))

Max Activating Token Index: 980

Text #18

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.3760. Min Act: -0.0000

Data Index: 134856 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 0.5544. Min Range: -0.5544

Max Act: 0.3633. Min Act: -0.0000

Data Index: 377153 (C4 (Web Text))

Max Activating Token Index: 494