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

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

Neuron 2302 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0424. Min Act: -0.0000

Data Index: 1206536 (C4 (Web Text))

Max Activating Token Index: 967

Text #1

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0368. Min Act: -0.0000

Data Index: 394346 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0340. Min Act: -0.0000

Data Index: 1108284 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0312. Min Act: -0.0000

Data Index: 927300 (C4 (Web Text))

Max Activating Token Index: 25

Text #4

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0286. Min Act: -0.0000

Data Index: 108461 (C4 (Web Text))

Max Activating Token Index: 660

Text #5

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0302. Min Act: -0.0000

Data Index: 390752 (C4 (Web Text))

Max Activating Token Index: 495

Text #6

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0301. Min Act: -0.0000

Data Index: 1475483 (Python Code)

Max Activating Token Index: 828

Text #7

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0299. Min Act: -0.0000

Data Index: 978331 (C4 (Web Text))

Max Activating Token Index: 988

Text #8

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0284. Min Act: -0.0000

Data Index: 271145 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0282. Min Act: -0.0000

Data Index: 321500 (C4 (Web Text))

Max Activating Token Index: 899

Text #10

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0270. Min Act: -0.0000

Data Index: 280984 (C4 (Web Text))

Max Activating Token Index: 872

Text #11

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0280. Min Act: -0.0000

Data Index: 618480 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0267. Min Act: -0.0000

Data Index: 907002 (C4 (Web Text))

Max Activating Token Index: 100

Text #13

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0267. Min Act: -0.0000

Data Index: 314227 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0260. Min Act: -0.0000

Data Index: 234677 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0267. Min Act: -0.0000

Data Index: 1392430 (Python Code)

Max Activating Token Index: 825

Text #16

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0264. Min Act: -0.0000

Data Index: 800968 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0252. Min Act: -0.0000

Data Index: 1656357 (Python Code)

Max Activating Token Index: 23

Text #18

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0254. Min Act: -0.0000

Data Index: 1265828 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 0.0424. Min Range: -0.0424

Max Act: 0.0250. Min Act: -0.0000

Data Index: 1018376 (C4 (Web Text))

Max Activating Token Index: 712