Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 183 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0556. Min Act: -0.0006

Data Index: 480213 (C4 (Web Text))

Max Activating Token Index: 927

Text #1

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0532. Min Act: -0.0006

Data Index: 886000 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0530. Min Act: -0.0006

Data Index: 53824 (C4 (Web Text))

Max Activating Token Index: 682

Text #3

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0552. Min Act: -0.0006

Data Index: 798881 (C4 (Web Text))

Max Activating Token Index: 761

Text #4

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0542. Min Act: -0.0006

Data Index: 759548 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0554. Min Act: -0.0006

Data Index: 747650 (C4 (Web Text))

Max Activating Token Index: 865

Text #6

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0546. Min Act: -0.0006

Data Index: 1107548 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0532. Min Act: -0.0006

Data Index: 1043403 (C4 (Web Text))

Max Activating Token Index: 375

Text #8

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0537. Min Act: -0.0006

Data Index: 525210 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0501. Min Act: -0.0006

Data Index: 1325028 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0506. Min Act: -0.0006

Data Index: 653972 (C4 (Web Text))

Max Activating Token Index: 417

Text #11

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0516. Min Act: -0.0006

Data Index: 417871 (C4 (Web Text))

Max Activating Token Index: 769

Text #12

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0496. Min Act: -0.0006

Data Index: 56266 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0505. Min Act: -0.0006

Data Index: 348092 (C4 (Web Text))

Max Activating Token Index: 354

Text #14

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0501. Min Act: -0.0006

Data Index: 1349581 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0498. Min Act: -0.0006

Data Index: 504356 (C4 (Web Text))

Max Activating Token Index: 364

Text #16

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0498. Min Act: -0.0006

Data Index: 754861 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0510. Min Act: -0.0006

Data Index: 328780 (C4 (Web Text))

Max Activating Token Index: 252

Text #18

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0495. Min Act: -0.0006

Data Index: 1009822 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 0.0556. Min Range: -0.0556

Max Act: 0.0517. Min Act: -0.0006

Data Index: 734021 (C4 (Web Text))

Max Activating Token Index: 816