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

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

Neuron 4382 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0325. Min Act: -0.0001

Data Index: 1635260 (Python Code)

Max Activating Token Index: 575

Text #1

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0314. Min Act: -0.0000

Data Index: 1650777 (Python Code)

Max Activating Token Index: 670

Text #2

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0304. Min Act: -0.0000

Data Index: 552579 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0297. Min Act: -0.0000

Data Index: 1433773 (Python Code)

Max Activating Token Index: 962

Text #4

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0311. Min Act: -0.0000

Data Index: 899727 (C4 (Web Text))

Max Activating Token Index: 497

Text #5

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0314. Min Act: -0.0001

Data Index: 553168 (C4 (Web Text))

Max Activating Token Index: 481

Text #6

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0309. Min Act: -0.0000

Data Index: 1261246 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0294. Min Act: -0.0001

Data Index: 914759 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0220. Min Act: -0.0001

Data Index: 350964 (C4 (Web Text))

Max Activating Token Index: 773

Text #9

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0286. Min Act: -0.0000

Data Index: 480164 (C4 (Web Text))

Max Activating Token Index: 41

Text #10

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0259. Min Act: -0.0000

Data Index: 52630 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0272. Min Act: -0.0000

Data Index: 1448767 (Python Code)

Max Activating Token Index: 532

Text #12

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0268. Min Act: -0.0000

Data Index: 408846 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0254. Min Act: -0.0000

Data Index: 1547542 (Python Code)

Max Activating Token Index: 408

Text #14

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0230. Min Act: -0.0001

Data Index: 1496233 (Python Code)

Max Activating Token Index: 200

Text #15

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0235. Min Act: -0.0001

Data Index: 1494206 (Python Code)

Max Activating Token Index: 678

Text #16

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0252. Min Act: -0.0001

Data Index: 861717 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0267. Min Act: -0.0001

Data Index: 1136610 (C4 (Web Text))

Max Activating Token Index: 412

Text #18

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0258. Min Act: -0.0001

Data Index: 70234 (C4 (Web Text))

Max Activating Token Index: 550

Text #19

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0261. Min Act: -0.0000

Data Index: 172329 (C4 (Web Text))

Max Activating Token Index: 23