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

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

Neuron 1932 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: 0.0655. Min Range: -0.0655

Max Act: 0.0655. Min Act: -0.0002

Data Index: 1537761 (Python Code)

Max Activating Token Index: 401

Text #1

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0591. Min Act: -0.0002

Data Index: 814831 (C4 (Web Text))

Max Activating Token Index: 586

Text #2

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0650. Min Act: -0.0002

Data Index: 1438 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0627. Min Act: -0.0001

Data Index: 81823 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0605. Min Act: -0.0001

Data Index: 1198219 (C4 (Web Text))

Max Activating Token Index: 913

Text #5

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0609. Min Act: -0.0002

Data Index: 1295490 (C4 (Web Text))

Max Activating Token Index: 227

Text #6

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0518. Min Act: -0.0002

Data Index: 14465 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0575. Min Act: -0.0002

Data Index: 682622 (C4 (Web Text))

Max Activating Token Index: 877

Text #8

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0564. Min Act: -0.0002

Data Index: 151319 (C4 (Web Text))

Max Activating Token Index: 436

Text #9

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0551. Min Act: -0.0002

Data Index: 1395900 (Python Code)

Max Activating Token Index: 400

Text #10

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0581. Min Act: -0.0001

Data Index: 861151 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0596. Min Act: -0.0002

Data Index: 227281 (C4 (Web Text))

Max Activating Token Index: 94

Text #12

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0510. Min Act: -0.0002

Data Index: 147534 (C4 (Web Text))

Max Activating Token Index: 603

Text #13

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0567. Min Act: -0.0001

Data Index: 1135890 (C4 (Web Text))

Max Activating Token Index: 725

Text #14

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0565. Min Act: -0.0002

Data Index: 249331 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0591. Min Act: -0.0001

Data Index: 17334 (C4 (Web Text))

Max Activating Token Index: 373

Text #16

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0521. Min Act: -0.0002

Data Index: 1435527 (Python Code)

Max Activating Token Index: 1007

Text #17

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0580. Min Act: -0.0002

Data Index: 471505 (C4 (Web Text))

Max Activating Token Index: 717

Text #18

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0577. Min Act: -0.0002

Data Index: 1206014 (C4 (Web Text))

Max Activating Token Index: 896

Text #19

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0533. Min Act: -0.0002

Data Index: 714875 (C4 (Web Text))

Max Activating Token Index: 582