Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1673 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0645. Min Act: -0.0003

Data Index: 1231934 (C4 (Web Text))

Max Activating Token Index: 574

Text #1

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0654. Min Act: -0.0003

Data Index: 714958 (C4 (Web Text))

Max Activating Token Index: 502

Text #2

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0585. Min Act: -0.0003

Data Index: 702334 (C4 (Web Text))

Max Activating Token Index: 471

Text #3

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0578. Min Act: -0.0003

Data Index: 770329 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0550. Min Act: -0.0003

Data Index: 508871 (C4 (Web Text))

Max Activating Token Index: 911

Text #5

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0540. Min Act: -0.0003

Data Index: 988545 (C4 (Web Text))

Max Activating Token Index: 754

Text #6

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0513. Min Act: -0.0003

Data Index: 1228163 (C4 (Web Text))

Max Activating Token Index: 486

Text #7

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0532. Min Act: -0.0004

Data Index: 1075572 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0530. Min Act: -0.0003

Data Index: 1153049 (C4 (Web Text))

Max Activating Token Index: 692

Text #9

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0526. Min Act: -0.0003

Data Index: 366216 (C4 (Web Text))

Max Activating Token Index: 585

Text #10

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0512. Min Act: -0.0003

Data Index: 297116 (C4 (Web Text))

Max Activating Token Index: 420

Text #11

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0530. Min Act: -0.0003

Data Index: 1047364 (C4 (Web Text))

Max Activating Token Index: 569

Text #12

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0524. Min Act: -0.0003

Data Index: 1377799 (Python Code)

Max Activating Token Index: 40

Text #13

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0491. Min Act: -0.0003

Data Index: 1174046 (C4 (Web Text))

Max Activating Token Index: 973

Text #14

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0515. Min Act: -0.0003

Data Index: 549934 (C4 (Web Text))

Max Activating Token Index: 322

Text #15

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0514. Min Act: -0.0003

Data Index: 1569333 (Python Code)

Max Activating Token Index: 5

Text #16

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0463. Min Act: -0.0003

Data Index: 932016 (C4 (Web Text))

Max Activating Token Index: 778

Text #17

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0522. Min Act: -0.0003

Data Index: 1143258 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0508. Min Act: -0.0003

Data Index: 1590719 (Python Code)

Max Activating Token Index: 132

Text #19

Max Range: 0.0654. Min Range: -0.0654

Max Act: 0.0456. Min Act: -0.0004

Data Index: 1353522 (C4 (Web Text))

Max Activating Token Index: 799