Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 865 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0687. Min Act: -0.0002

Data Index: 1461419 (Python Code)

Max Activating Token Index: 61

Text #1

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0699. Min Act: -0.0002

Data Index: 515363 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1385768 (Python Code)

Max Activating Token Index: 60

Text #3

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0680. Min Act: -0.0002

Data Index: 1486034 (Python Code)

Max Activating Token Index: 216

Text #4

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0668. Min Act: -0.0002

Data Index: 1437498 (Python Code)

Max Activating Token Index: 42

Text #5

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0653. Min Act: -0.0002

Data Index: 1383386 (Python Code)

Max Activating Token Index: 136

Text #6

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0631. Min Act: -0.0002

Data Index: 1420010 (Python Code)

Max Activating Token Index: 592

Text #7

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0649. Min Act: -0.0002

Data Index: 1412424 (Python Code)

Max Activating Token Index: 585

Text #8

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0649. Min Act: -0.0002

Data Index: 1522080 (Python Code)

Max Activating Token Index: 98

Text #9

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0634. Min Act: -0.0002

Data Index: 1592530 (Python Code)

Max Activating Token Index: 60

Text #10

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0648. Min Act: -0.0002

Data Index: 1639294 (Python Code)

Max Activating Token Index: 331

Text #11

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0639. Min Act: -0.0002

Data Index: 1581850 (Python Code)

Max Activating Token Index: 124

Text #12

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0622. Min Act: -0.0002

Data Index: 1499459 (Python Code)

Max Activating Token Index: 21

Text #13

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0655. Min Act: -0.0002

Data Index: 1484065 (Python Code)

Max Activating Token Index: 73

Text #14

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0629. Min Act: -0.0002

Data Index: 981282 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0624. Min Act: -0.0002

Data Index: 1600462 (Python Code)

Max Activating Token Index: 379

Text #16

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0602. Min Act: -0.0002

Data Index: 370565 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0613. Min Act: -0.0002

Data Index: 509766 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0621. Min Act: -0.0002

Data Index: 1381386 (Python Code)

Max Activating Token Index: 124

Text #19

Max Range: 0.0699. Min Range: -0.0699

Max Act: 0.0625. Min Act: -0.0002

Data Index: 1417109 (Python Code)

Max Activating Token Index: 601