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

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

Neuron 4491 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: 4.5709. Min Range: -4.5709

Max Act: 4.4306. Min Act: -0.0000

Data Index: 754923 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 4.5709. Min Range: -4.5709

Max Act: 4.5709. Min Act: -0.0000

Data Index: 176431 (C4 (Web Text))

Max Activating Token Index: 117

Text #2

Max Range: 4.5709. Min Range: -4.5709

Max Act: 4.2529. Min Act: -0.0000

Data Index: 1653592 (Python Code)

Max Activating Token Index: 510

Text #3

Max Range: 4.5709. Min Range: -4.5709

Max Act: 4.1749. Min Act: -0.0000

Data Index: 1189434 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 4.5709. Min Range: -4.5709

Max Act: 3.7634. Min Act: -0.0000

Data Index: 201760 (C4 (Web Text))

Max Activating Token Index: 263

Text #5

Max Range: 4.5709. Min Range: -4.5709

Max Act: 3.9523. Min Act: -0.0000

Data Index: 790393 (C4 (Web Text))

Max Activating Token Index: 291

Text #6

Max Range: 4.5709. Min Range: -4.5709

Max Act: 4.0747. Min Act: -0.0000

Data Index: 1451769 (Python Code)

Max Activating Token Index: 624

Text #7

Max Range: 4.5709. Min Range: -4.5709

Max Act: 3.8960. Min Act: -0.0000

Data Index: 665743 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 4.5709. Min Range: -4.5709

Max Act: 4.0639. Min Act: -0.0000

Data Index: 1643890 (Python Code)

Max Activating Token Index: 351

Text #9

Max Range: 4.5709. Min Range: -4.5709

Max Act: 4.0128. Min Act: -0.0000

Data Index: 529117 (C4 (Web Text))

Max Activating Token Index: 100

Text #10

Max Range: 4.5709. Min Range: -4.5709

Max Act: 3.8734. Min Act: -0.0000

Data Index: 194451 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 4.5709. Min Range: -4.5709

Max Act: 4.1083. Min Act: -0.0000

Data Index: 1444232 (Python Code)

Max Activating Token Index: 898

Text #12

Max Range: 4.5709. Min Range: -4.5709

Max Act: 3.7684. Min Act: -0.0000

Data Index: 624591 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 4.5709. Min Range: -4.5709

Max Act: 3.7637. Min Act: -0.0000

Data Index: 1626179 (Python Code)

Max Activating Token Index: 589

Text #14

Max Range: 4.5709. Min Range: -4.5709

Max Act: 3.9061. Min Act: -0.0000

Data Index: 1554618 (Python Code)

Max Activating Token Index: 107

Text #15

Max Range: 4.5709. Min Range: -4.5709

Max Act: 3.8930. Min Act: -0.0000

Data Index: 1642583 (Python Code)

Max Activating Token Index: 488

Text #16

Max Range: 4.5709. Min Range: -4.5709

Max Act: 4.0100. Min Act: -0.0000

Data Index: 1273731 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 4.5709. Min Range: -4.5709

Max Act: 4.0506. Min Act: -0.0000

Data Index: 625513 (C4 (Web Text))

Max Activating Token Index: 636

Text #18

Max Range: 4.5709. Min Range: -4.5709

Max Act: 3.8684. Min Act: -0.0000

Data Index: 1329603 (C4 (Web Text))

Max Activating Token Index: 739

Text #19

Max Range: 4.5709. Min Range: -4.5709

Max Act: 4.0028. Min Act: -0.0000

Data Index: 1060413 (C4 (Web Text))

Max Activating Token Index: 231