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

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

Neuron 3455 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: 1.2829. Min Range: -1.2829

Max Act: 1.2829. Min Act: -0.0002

Data Index: 1180325 (C4 (Web Text))

Max Activating Token Index: 767

Text #1

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.1947. Min Act: -0.0002

Data Index: 338658 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.2063. Min Act: -0.0002

Data Index: 549572 (C4 (Web Text))

Max Activating Token Index: 800

Text #3

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.1734. Min Act: -0.0002

Data Index: 297329 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.1726. Min Act: -0.0002

Data Index: 83201 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.1670. Min Act: -0.0002

Data Index: 38007 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.1576. Min Act: -0.0002

Data Index: 286995 (C4 (Web Text))

Max Activating Token Index: 659

Text #7

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.1097. Min Act: -0.0002

Data Index: 621587 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.0919. Min Act: -0.0002

Data Index: 425623 (C4 (Web Text))

Max Activating Token Index: 635

Text #9

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.0981. Min Act: -0.0002

Data Index: 1169173 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.0885. Min Act: -0.0002

Data Index: 255151 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.0975. Min Act: -0.0002

Data Index: 71275 (C4 (Web Text))

Max Activating Token Index: 708

Text #12

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.0904. Min Act: -0.0002

Data Index: 1321802 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.1221. Min Act: -0.0002

Data Index: 997391 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.0745. Min Act: -0.0002

Data Index: 1185464 (C4 (Web Text))

Max Activating Token Index: 916

Text #15

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.0642. Min Act: -0.0002

Data Index: 1150573 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.0811. Min Act: -0.0002

Data Index: 1198539 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.0323. Min Act: -0.0002

Data Index: 575658 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.0389. Min Act: -0.0002

Data Index: 469280 (C4 (Web Text))

Max Activating Token Index: 589

Text #19

Max Range: 1.2829. Min Range: -1.2829

Max Act: 1.0444. Min Act: -0.0002

Data Index: 494081 (C4 (Web Text))

Max Activating Token Index: 752