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

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

Neuron 772 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0825. Min Act: -0.0003

Data Index: 132602 (C4 (Web Text))

Max Activating Token Index: 471

Text #1

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0719. Min Act: -0.0003

Data Index: 481942 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0718. Min Act: -0.0003

Data Index: 1288060 (C4 (Web Text))

Max Activating Token Index: 627

Text #3

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0726. Min Act: -0.0003

Data Index: 5932 (C4 (Web Text))

Max Activating Token Index: 452

Text #4

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0670. Min Act: -0.0003

Data Index: 968261 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0643. Min Act: -0.0003

Data Index: 1316942 (C4 (Web Text))

Max Activating Token Index: 912

Text #6

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0578. Min Act: -0.0003

Data Index: 688615 (C4 (Web Text))

Max Activating Token Index: 517

Text #7

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0573. Min Act: -0.0003

Data Index: 860451 (C4 (Web Text))

Max Activating Token Index: 317

Text #8

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0561. Min Act: -0.0003

Data Index: 1258312 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0583. Min Act: -0.0003

Data Index: 1252606 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0552. Min Act: -0.0003

Data Index: 573393 (C4 (Web Text))

Max Activating Token Index: 251

Text #11

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0560. Min Act: -0.0002

Data Index: 1348677 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0539. Min Act: -0.0003

Data Index: 237832 (C4 (Web Text))

Max Activating Token Index: 485

Text #13

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0571. Min Act: -0.0003

Data Index: 632701 (C4 (Web Text))

Max Activating Token Index: 953

Text #14

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0536. Min Act: -0.0002

Data Index: 917030 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0545. Min Act: -0.0003

Data Index: 569906 (C4 (Web Text))

Max Activating Token Index: 200

Text #16

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0525. Min Act: -0.0003

Data Index: 776705 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0531. Min Act: -0.0003

Data Index: 1012947 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0546. Min Act: -0.0003

Data Index: 155943 (C4 (Web Text))

Max Activating Token Index: 376

Text #19

Max Range: 0.0825. Min Range: -0.0825

Max Act: 0.0554. Min Act: -0.0002

Data Index: 754145 (C4 (Web Text))

Max Activating Token Index: 767