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

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

Neuron 2161 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4698. Min Act: -0.0001

Data Index: 1507303 (Python Code)

Max Activating Token Index: 49

Text #1

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.4284. Min Act: -0.0001

Data Index: 1481795 (Python Code)

Max Activating Token Index: 298

Text #2

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3854. Min Act: -0.0001

Data Index: 1579026 (Python Code)

Max Activating Token Index: 58

Text #3

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3743. Min Act: -0.0001

Data Index: 1590091 (Python Code)

Max Activating Token Index: 617

Text #4

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3776. Min Act: -0.0001

Data Index: 1630968 (Python Code)

Max Activating Token Index: 373

Text #5

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3603. Min Act: -0.0001

Data Index: 1643411 (Python Code)

Max Activating Token Index: 950

Text #6

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3695. Min Act: -0.0001

Data Index: 1609930 (Python Code)

Max Activating Token Index: 464

Text #7

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3771. Min Act: -0.0001

Data Index: 1519954 (Python Code)

Max Activating Token Index: 68

Text #8

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3679. Min Act: -0.0001

Data Index: 1448474 (Python Code)

Max Activating Token Index: 175

Text #9

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3449. Min Act: -0.0001

Data Index: 1542718 (Python Code)

Max Activating Token Index: 47

Text #10

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3653. Min Act: -0.0001

Data Index: 1394395 (Python Code)

Max Activating Token Index: 828

Text #11

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3531. Min Act: -0.0001

Data Index: 1389963 (Python Code)

Max Activating Token Index: 503

Text #12

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3502. Min Act: -0.0001

Data Index: 1531005 (Python Code)

Max Activating Token Index: 441

Text #13

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3744. Min Act: -0.0001

Data Index: 1589477 (Python Code)

Max Activating Token Index: 566

Text #14

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3472. Min Act: -0.0001

Data Index: 1412690 (Python Code)

Max Activating Token Index: 463

Text #15

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3501. Min Act: -0.0001

Data Index: 1631358 (Python Code)

Max Activating Token Index: 559

Text #16

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3422. Min Act: -0.0001

Data Index: 1375566 (Python Code)

Max Activating Token Index: 351

Text #17

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3285. Min Act: -0.0001

Data Index: 1515842 (Python Code)

Max Activating Token Index: 1013

Text #18

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3422. Min Act: -0.0001

Data Index: 1614751 (Python Code)

Max Activating Token Index: 224

Text #19

Max Range: 0.4698. Min Range: -0.4698

Max Act: 0.3517. Min Act: -0.0001

Data Index: 1491481 (Python Code)

Max Activating Token Index: 577