Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1014 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0594. Min Act: -0.0003

Data Index: 1119511 (C4 (Web Text))

Max Activating Token Index: 439

Text #1

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0567. Min Act: -0.0003

Data Index: 14416 (C4 (Web Text))

Max Activating Token Index: 777

Text #2

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0575. Min Act: -0.0003

Data Index: 1236454 (C4 (Web Text))

Max Activating Token Index: 645

Text #3

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0565. Min Act: -0.0003

Data Index: 330077 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0551. Min Act: -0.0003

Data Index: 339854 (C4 (Web Text))

Max Activating Token Index: 589

Text #5

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0559. Min Act: -0.0003

Data Index: 633181 (C4 (Web Text))

Max Activating Token Index: 361

Text #6

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0558. Min Act: -0.0003

Data Index: 342612 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0540. Min Act: -0.0003

Data Index: 632180 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0533. Min Act: -0.0003

Data Index: 451481 (C4 (Web Text))

Max Activating Token Index: 496

Text #9

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0543. Min Act: -0.0003

Data Index: 1144908 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0538. Min Act: -0.0003

Data Index: 1138948 (C4 (Web Text))

Max Activating Token Index: 261

Text #11

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0527. Min Act: -0.0003

Data Index: 957717 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0533. Min Act: -0.0003

Data Index: 726791 (C4 (Web Text))

Max Activating Token Index: 439

Text #13

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0529. Min Act: -0.0003

Data Index: 972592 (C4 (Web Text))

Max Activating Token Index: 568

Text #14

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0523. Min Act: -0.0003

Data Index: 1222954 (C4 (Web Text))

Max Activating Token Index: 486

Text #15

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0522. Min Act: -0.0003

Data Index: 571427 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0510. Min Act: -0.0003

Data Index: 1308509 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0518. Min Act: -0.0003

Data Index: 156497 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0515. Min Act: -0.0003

Data Index: 586722 (C4 (Web Text))

Max Activating Token Index: 476

Text #19

Max Range: 0.0594. Min Range: -0.0594

Max Act: 0.0511. Min Act: -0.0003

Data Index: 923482 (C4 (Web Text))

Max Activating Token Index: 327