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

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

Neuron 42 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: 0.1774. Min Range: -0.1774

Max Act: 0.1726. Min Act: -0.0001

Data Index: 197690 (C4 (Web Text))

Max Activating Token Index: 920

Text #1

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1633. Min Act: -0.0001

Data Index: 744498 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1673. Min Act: -0.0002

Data Index: 542518 (C4 (Web Text))

Max Activating Token Index: 397

Text #3

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1737. Min Act: -0.0002

Data Index: 182561 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1774. Min Act: -0.0002

Data Index: 1006715 (C4 (Web Text))

Max Activating Token Index: 843

Text #5

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1684. Min Act: -0.0002

Data Index: 64587 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1624. Min Act: -0.0002

Data Index: 224242 (C4 (Web Text))

Max Activating Token Index: 36

Text #7

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1725. Min Act: -0.0002

Data Index: 1304531 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1670. Min Act: -0.0001

Data Index: 267230 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1634. Min Act: -0.0002

Data Index: 669969 (C4 (Web Text))

Max Activating Token Index: 54

Text #10

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1613. Min Act: -0.0002

Data Index: 252584 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1595. Min Act: -0.0002

Data Index: 1049936 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1612. Min Act: -0.0002

Data Index: 989680 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1595. Min Act: -0.0002

Data Index: 610750 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1648. Min Act: -0.0002

Data Index: 209774 (C4 (Web Text))

Max Activating Token Index: 200

Text #15

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1582. Min Act: -0.0002

Data Index: 16553 (C4 (Web Text))

Max Activating Token Index: 898

Text #16

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1584. Min Act: -0.0002

Data Index: 701414 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1600. Min Act: -0.0002

Data Index: 952842 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1559. Min Act: -0.0002

Data Index: 566674 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 0.1774. Min Range: -0.1774

Max Act: 0.1672. Min Act: -0.0002

Data Index: 470765 (C4 (Web Text))

Max Activating Token Index: 604