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

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

Neuron 1881 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: 0.0722. Min Range: -0.0722

Max Act: 0.0722. Min Act: -0.0002

Data Index: 963526 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0689. Min Act: -0.0002

Data Index: 6816 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0616. Min Act: -0.0001

Data Index: 400117 (C4 (Web Text))

Max Activating Token Index: 513

Text #3

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0609. Min Act: -0.0002

Data Index: 470196 (C4 (Web Text))

Max Activating Token Index: 464

Text #4

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0587. Min Act: -0.0001

Data Index: 529404 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0603. Min Act: -0.0002

Data Index: 302738 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0555. Min Act: -0.0001

Data Index: 136309 (C4 (Web Text))

Max Activating Token Index: 500

Text #7

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0558. Min Act: -0.0002

Data Index: 264847 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0621. Min Act: -0.0002

Data Index: 1329930 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0600. Min Act: -0.0002

Data Index: 159064 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0537. Min Act: -0.0002

Data Index: 81878 (C4 (Web Text))

Max Activating Token Index: 629

Text #11

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0533. Min Act: -0.0002

Data Index: 1159182 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0569. Min Act: -0.0001

Data Index: 88042 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0586. Min Act: -0.0002

Data Index: 605276 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0533. Min Act: -0.0001

Data Index: 1299866 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0563. Min Act: -0.0002

Data Index: 662091 (C4 (Web Text))

Max Activating Token Index: 843

Text #16

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0510. Min Act: -0.0002

Data Index: 1288581 (C4 (Web Text))

Max Activating Token Index: 671

Text #17

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0535. Min Act: -0.0002

Data Index: 867144 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0537. Min Act: -0.0001

Data Index: 944495 (C4 (Web Text))

Max Activating Token Index: 131

Text #19

Max Range: 0.0722. Min Range: -0.0722

Max Act: 0.0515. Min Act: -0.0001

Data Index: 1030190 (C4 (Web Text))

Max Activating Token Index: 756