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

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

Neuron 5926 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0648. Min Act: -0.0002

Data Index: 394715 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0645. Min Act: -0.0002

Data Index: 887026 (C4 (Web Text))

Max Activating Token Index: 220

Text #2

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0655. Min Act: -0.0002

Data Index: 121643 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0640. Min Act: -0.0003

Data Index: 221124 (C4 (Web Text))

Max Activating Token Index: 198

Text #4

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0629. Min Act: -0.0002

Data Index: 236074 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0612. Min Act: -0.0002

Data Index: 705709 (C4 (Web Text))

Max Activating Token Index: 654

Text #6

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0621. Min Act: -0.0002

Data Index: 1198844 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0616. Min Act: -0.0002

Data Index: 525275 (C4 (Web Text))

Max Activating Token Index: 253

Text #8

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0615. Min Act: -0.0002

Data Index: 433394 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0607. Min Act: -0.0002

Data Index: 1235574 (C4 (Web Text))

Max Activating Token Index: 50

Text #10

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0605. Min Act: -0.0002

Data Index: 1176736 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0609. Min Act: -0.0002

Data Index: 760949 (C4 (Web Text))

Max Activating Token Index: 113

Text #12

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0614. Min Act: -0.0002

Data Index: 822444 (C4 (Web Text))

Max Activating Token Index: 702

Text #13

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0589. Min Act: -0.0002

Data Index: 899199 (C4 (Web Text))

Max Activating Token Index: 623

Text #14

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0592. Min Act: -0.0002

Data Index: 454561 (C4 (Web Text))

Max Activating Token Index: 896

Text #15

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0588. Min Act: -0.0002

Data Index: 112587 (C4 (Web Text))

Max Activating Token Index: 890

Text #16

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0575. Min Act: -0.0002

Data Index: 612048 (C4 (Web Text))

Max Activating Token Index: 976

Text #17

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0567. Min Act: -0.0002

Data Index: 736094 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0579. Min Act: -0.0002

Data Index: 1098050 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 0.0655. Min Range: -0.0655

Max Act: 0.0573. Min Act: -0.0002

Data Index: 391926 (C4 (Web Text))

Max Activating Token Index: 600