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

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

Neuron 4932 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: 0.2820. Min Range: -0.2820

Max Act: 0.2820. Min Act: -0.0000

Data Index: 1545586 (Python Code)

Max Activating Token Index: 662

Text #1

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2716. Min Act: -0.0000

Data Index: 1583541 (Python Code)

Max Activating Token Index: 483

Text #2

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2577. Min Act: -0.0000

Data Index: 1523857 (Python Code)

Max Activating Token Index: 862

Text #3

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2575. Min Act: -0.0000

Data Index: 259300 (C4 (Web Text))

Max Activating Token Index: 85

Text #4

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2412. Min Act: -0.0000

Data Index: 1486790 (Python Code)

Max Activating Token Index: 73

Text #5

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2455. Min Act: -0.0000

Data Index: 1500311 (Python Code)

Max Activating Token Index: 206

Text #6

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2356. Min Act: -0.0000

Data Index: 1531561 (Python Code)

Max Activating Token Index: 995

Text #7

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2365. Min Act: -0.0000

Data Index: 665547 (C4 (Web Text))

Max Activating Token Index: 1001

Text #8

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2339. Min Act: -0.0000

Data Index: 1607495 (Python Code)

Max Activating Token Index: 155

Text #9

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2445. Min Act: -0.0000

Data Index: 628630 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2237. Min Act: -0.0000

Data Index: 496456 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2206. Min Act: -0.0000

Data Index: 1470861 (Python Code)

Max Activating Token Index: 737

Text #12

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2287. Min Act: -0.0000

Data Index: 1577715 (Python Code)

Max Activating Token Index: 408

Text #13

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2259. Min Act: -0.0000

Data Index: 219649 (C4 (Web Text))

Max Activating Token Index: 935

Text #14

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2305. Min Act: -0.0000

Data Index: 1373295 (Python Code)

Max Activating Token Index: 419

Text #15

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2241. Min Act: -0.0000

Data Index: 1653617 (Python Code)

Max Activating Token Index: 812

Text #16

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2359. Min Act: -0.0000

Data Index: 789712 (C4 (Web Text))

Max Activating Token Index: 798

Text #17

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2200. Min Act: -0.0000

Data Index: 1579619 (Python Code)

Max Activating Token Index: 811

Text #18

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2117. Min Act: -0.0000

Data Index: 1502751 (Python Code)

Max Activating Token Index: 848

Text #19

Max Range: 0.2820. Min Range: -0.2820

Max Act: 0.2247. Min Act: -0.0000

Data Index: 1521719 (Python Code)

Max Activating Token Index: 436