Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2883 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0648. Min Act: -0.0002

Data Index: 1277048 (C4 (Web Text))

Max Activating Token Index: 87

Text #1

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0495. Min Act: -0.0002

Data Index: 355763 (C4 (Web Text))

Max Activating Token Index: 317

Text #2

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0534. Min Act: -0.0002

Data Index: 408024 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0516. Min Act: -0.0002

Data Index: 314794 (C4 (Web Text))

Max Activating Token Index: 417

Text #4

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0507. Min Act: -0.0002

Data Index: 824526 (C4 (Web Text))

Max Activating Token Index: 561

Text #5

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0504. Min Act: -0.0002

Data Index: 1023680 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0461. Min Act: -0.0002

Data Index: 443454 (C4 (Web Text))

Max Activating Token Index: 671

Text #7

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0523. Min Act: -0.0002

Data Index: 1036469 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0520. Min Act: -0.0002

Data Index: 98143 (C4 (Web Text))

Max Activating Token Index: 315

Text #9

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0496. Min Act: -0.0002

Data Index: 1322142 (C4 (Web Text))

Max Activating Token Index: 223

Text #10

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0505. Min Act: -0.0002

Data Index: 1167131 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0467. Min Act: -0.0002

Data Index: 998017 (C4 (Web Text))

Max Activating Token Index: 637

Text #12

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0464. Min Act: -0.0002

Data Index: 703993 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0476. Min Act: -0.0002

Data Index: 37877 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0498. Min Act: -0.0002

Data Index: 1335247 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0473. Min Act: -0.0002

Data Index: 1017204 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0473. Min Act: -0.0002

Data Index: 617344 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0472. Min Act: -0.0002

Data Index: 1358695 (C4 (Web Text))

Max Activating Token Index: 469

Text #18

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0472. Min Act: -0.0002

Data Index: 72071 (C4 (Web Text))

Max Activating Token Index: 804

Text #19

Max Range: 0.0648. Min Range: -0.0648

Max Act: 0.0514. Min Act: -0.0002

Data Index: 727334 (C4 (Web Text))

Max Activating Token Index: 595