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

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

Neuron 593 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: 0.0534. Min Range: -0.0534

Max Act: 0.0527. Min Act: -0.0006

Data Index: 249826 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0534. Min Act: -0.0006

Data Index: 613946 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0476. Min Act: -0.0006

Data Index: 282165 (C4 (Web Text))

Max Activating Token Index: 72

Text #3

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0488. Min Act: -0.0006

Data Index: 570706 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0464. Min Act: -0.0006

Data Index: 247795 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0453. Min Act: -0.0006

Data Index: 927852 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0481. Min Act: -0.0006

Data Index: 1081267 (C4 (Web Text))

Max Activating Token Index: 738

Text #7

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0491. Min Act: -0.0006

Data Index: 72551 (C4 (Web Text))

Max Activating Token Index: 677

Text #8

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0444. Min Act: -0.0006

Data Index: 640593 (C4 (Web Text))

Max Activating Token Index: 59

Text #9

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0467. Min Act: -0.0006

Data Index: 826120 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0484. Min Act: -0.0006

Data Index: 1241461 (C4 (Web Text))

Max Activating Token Index: 627

Text #11

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0472. Min Act: -0.0006

Data Index: 683873 (C4 (Web Text))

Max Activating Token Index: 579

Text #12

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0454. Min Act: -0.0006

Data Index: 869631 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0444. Min Act: -0.0006

Data Index: 628135 (C4 (Web Text))

Max Activating Token Index: 337

Text #14

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0426. Min Act: -0.0006

Data Index: 680301 (C4 (Web Text))

Max Activating Token Index: 878

Text #15

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0451. Min Act: -0.0006

Data Index: 1357705 (C4 (Web Text))

Max Activating Token Index: 953

Text #16

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0467. Min Act: -0.0006

Data Index: 661735 (C4 (Web Text))

Max Activating Token Index: 669

Text #17

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0454. Min Act: -0.0006

Data Index: 254331 (C4 (Web Text))

Max Activating Token Index: 832

Text #18

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0434. Min Act: -0.0005

Data Index: 683626 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 0.0534. Min Range: -0.0534

Max Act: 0.0458. Min Act: -0.0006

Data Index: 489838 (C4 (Web Text))

Max Activating Token Index: 80