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

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

Neuron 2164 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0739. Min Act: -0.0003

Data Index: 1046806 (C4 (Web Text))

Max Activating Token Index: 194

Text #1

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0747. Min Act: -0.0003

Data Index: 164866 (C4 (Web Text))

Max Activating Token Index: 158

Text #2

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0731. Min Act: -0.0003

Data Index: 1482277 (Python Code)

Max Activating Token Index: 65

Text #3

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0729. Min Act: -0.0003

Data Index: 1156341 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0719. Min Act: -0.0003

Data Index: 1509029 (Python Code)

Max Activating Token Index: 718

Text #5

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0702. Min Act: -0.0003

Data Index: 1649708 (Python Code)

Max Activating Token Index: 685

Text #6

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0667. Min Act: -0.0003

Data Index: 575977 (C4 (Web Text))

Max Activating Token Index: 377

Text #7

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0687. Min Act: -0.0003

Data Index: 902085 (C4 (Web Text))

Max Activating Token Index: 773

Text #8

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0662. Min Act: -0.0003

Data Index: 391618 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0666. Min Act: -0.0003

Data Index: 1368270 (Python Code)

Max Activating Token Index: 255

Text #10

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0657. Min Act: -0.0002

Data Index: 860780 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0639. Min Act: -0.0003

Data Index: 1457464 (Python Code)

Max Activating Token Index: 30

Text #12

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0636. Min Act: -0.0003

Data Index: 1401536 (Python Code)

Max Activating Token Index: 176

Text #13

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0632. Min Act: -0.0002

Data Index: 1361065 (Python Code)

Max Activating Token Index: 525

Text #14

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0623. Min Act: -0.0002

Data Index: 1385107 (Python Code)

Max Activating Token Index: 106

Text #15

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0626. Min Act: -0.0003

Data Index: 143366 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0623. Min Act: -0.0003

Data Index: 83895 (C4 (Web Text))

Max Activating Token Index: 729

Text #17

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0627. Min Act: -0.0003

Data Index: 1569920 (Python Code)

Max Activating Token Index: 344

Text #18

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0602. Min Act: -0.0003

Data Index: 868992 (C4 (Web Text))

Max Activating Token Index: 963

Text #19

Max Range: 0.0747. Min Range: -0.0747

Max Act: 0.0603. Min Act: -0.0002

Data Index: 1594831 (Python Code)

Max Activating Token Index: 466