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

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

Neuron 1798 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: 0.9377. Min Range: -0.9377

Max Act: 0.9377. Min Act: -0.0000

Data Index: 1361275 (Python Code)

Max Activating Token Index: 955

Text #1

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.8354. Min Act: -0.0000

Data Index: 1380507 (Python Code)

Max Activating Token Index: 903

Text #2

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.8052. Min Act: -0.0000

Data Index: 1648396 (Python Code)

Max Activating Token Index: 673

Text #3

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.8328. Min Act: -0.0000

Data Index: 1655851 (Python Code)

Max Activating Token Index: 84

Text #4

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.8700. Min Act: -0.0000

Data Index: 1472130 (Python Code)

Max Activating Token Index: 716

Text #5

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.8086. Min Act: -0.0000

Data Index: 1559467 (Python Code)

Max Activating Token Index: 747

Text #6

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.7510. Min Act: -0.0000

Data Index: 1632535 (Python Code)

Max Activating Token Index: 548

Text #7

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.6923. Min Act: -0.0000

Data Index: 1548351 (Python Code)

Max Activating Token Index: 783

Text #8

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.7698. Min Act: -0.0000

Data Index: 1497978 (Python Code)

Max Activating Token Index: 578

Text #9

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.6997. Min Act: -0.0000

Data Index: 942869 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.7417. Min Act: -0.0000

Data Index: 1372581 (Python Code)

Max Activating Token Index: 47

Text #11

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.7797. Min Act: -0.0000

Data Index: 1642276 (Python Code)

Max Activating Token Index: 776

Text #12

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.7289. Min Act: -0.0000

Data Index: 1540789 (Python Code)

Max Activating Token Index: 294

Text #13

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.7255. Min Act: -0.0000

Data Index: 1557056 (Python Code)

Max Activating Token Index: 264

Text #14

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.7111. Min Act: -0.0000

Data Index: 1637912 (Python Code)

Max Activating Token Index: 788

Text #15

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.6983. Min Act: -0.0000

Data Index: 1646456 (Python Code)

Max Activating Token Index: 632

Text #16

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.6914. Min Act: -0.0000

Data Index: 1602676 (Python Code)

Max Activating Token Index: 475

Text #17

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.6394. Min Act: -0.0000

Data Index: 1452334 (Python Code)

Max Activating Token Index: 864

Text #18

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.7247. Min Act: -0.0000

Data Index: 1446168 (Python Code)

Max Activating Token Index: 625

Text #19

Max Range: 0.9377. Min Range: -0.9377

Max Act: 0.6807. Min Act: -0.0000

Data Index: 1474224 (Python Code)

Max Activating Token Index: 597