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

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

Neuron 5868 in Layer 0

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: 0.1779. Min Range: -0.1779

Max Act: 0.1779. Min Act: -0.0001

Data Index: 1236473 (C4 (Web Text))

Max Activating Token Index: 889

Text #1

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1722. Min Act: -0.0001

Data Index: 1193451 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1723. Min Act: -0.0001

Data Index: 233409 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1684. Min Act: -0.0001

Data Index: 387798 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1664. Min Act: -0.0001

Data Index: 1055734 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1636. Min Act: -0.0001

Data Index: 907189 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1625. Min Act: -0.0001

Data Index: 582916 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1584. Min Act: -0.0001

Data Index: 545376 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1568. Min Act: -0.0001

Data Index: 1258319 (C4 (Web Text))

Max Activating Token Index: 679

Text #9

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1532. Min Act: -0.0001

Data Index: 1205914 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1547. Min Act: -0.0001

Data Index: 443888 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1563. Min Act: -0.0001

Data Index: 74108 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1535. Min Act: -0.0001

Data Index: 275325 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1500. Min Act: -0.0001

Data Index: 687313 (C4 (Web Text))

Max Activating Token Index: 913

Text #14

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1530. Min Act: -0.0001

Data Index: 1082691 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1481. Min Act: -0.0001

Data Index: 1193337 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1481. Min Act: -0.0001

Data Index: 194532 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1474. Min Act: -0.0001

Data Index: 450394 (C4 (Web Text))

Max Activating Token Index: 453

Text #18

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1496. Min Act: -0.0001

Data Index: 1136483 (C4 (Web Text))

Max Activating Token Index: 244

Text #19

Max Range: 0.1779. Min Range: -0.1779

Max Act: 0.1466. Min Act: -0.0001

Data Index: 493044 (C4 (Web Text))

Max Activating Token Index: 671