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

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

Neuron 2080 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: 0.0751. Min Range: -0.0751

Max Act: 0.0751. Min Act: -0.0002

Data Index: 694492 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0734. Min Act: -0.0002

Data Index: 306148 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0706. Min Act: -0.0002

Data Index: 1230305 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0662. Min Act: -0.0002

Data Index: 500338 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0662. Min Act: -0.0002

Data Index: 976635 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0675. Min Act: -0.0002

Data Index: 1326136 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0649. Min Act: -0.0002

Data Index: 1243326 (C4 (Web Text))

Max Activating Token Index: 255

Text #7

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0640. Min Act: -0.0002

Data Index: 1118616 (C4 (Web Text))

Max Activating Token Index: 304

Text #8

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0621. Min Act: -0.0002

Data Index: 1343469 (C4 (Web Text))

Max Activating Token Index: 53

Text #9

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0618. Min Act: -0.0002

Data Index: 1014890 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0605. Min Act: -0.0002

Data Index: 269470 (C4 (Web Text))

Max Activating Token Index: 146

Text #11

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0582. Min Act: -0.0002

Data Index: 1203796 (C4 (Web Text))

Max Activating Token Index: 694

Text #12

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0588. Min Act: -0.0002

Data Index: 952777 (C4 (Web Text))

Max Activating Token Index: 1009

Text #13

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0570. Min Act: -0.0002

Data Index: 386146 (C4 (Web Text))

Max Activating Token Index: 758

Text #14

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0580. Min Act: -0.0002

Data Index: 928819 (C4 (Web Text))

Max Activating Token Index: 86

Text #15

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0573. Min Act: -0.0002

Data Index: 1298883 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0568. Min Act: -0.0002

Data Index: 473000 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0575. Min Act: -0.0002

Data Index: 404734 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0567. Min Act: -0.0002

Data Index: 695338 (C4 (Web Text))

Max Activating Token Index: 142

Text #19

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0571. Min Act: -0.0002

Data Index: 201060 (C4 (Web Text))

Max Activating Token Index: 498