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

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

Neuron 86 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.5485. Min Act: -0.0000

Data Index: 730045 (C4 (Web Text))

Max Activating Token Index: 345

Text #1

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.4853. Min Act: -0.0000

Data Index: 1217588 (C4 (Web Text))

Max Activating Token Index: 476

Text #2

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.4607. Min Act: -0.0000

Data Index: 458060 (C4 (Web Text))

Max Activating Token Index: 445

Text #3

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.4482. Min Act: -0.0000

Data Index: 559573 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.4060. Min Act: -0.0000

Data Index: 1028805 (C4 (Web Text))

Max Activating Token Index: 57

Text #5

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.3950. Min Act: -0.0000

Data Index: 945081 (C4 (Web Text))

Max Activating Token Index: 789

Text #6

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.3908. Min Act: -0.0000

Data Index: 546633 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.3405. Min Act: -0.0000

Data Index: 275232 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.3870. Min Act: -0.0000

Data Index: 33877 (C4 (Web Text))

Max Activating Token Index: 894

Text #9

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.3665. Min Act: -0.0000

Data Index: 1067342 (C4 (Web Text))

Max Activating Token Index: 486

Text #10

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.3565. Min Act: -0.0000

Data Index: 1131822 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.3415. Min Act: -0.0000

Data Index: 683816 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.3561. Min Act: -0.0000

Data Index: 1193750 (C4 (Web Text))

Max Activating Token Index: 370

Text #13

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.3771. Min Act: -0.0000

Data Index: 533626 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.3504. Min Act: -0.0000

Data Index: 1328548 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.3132. Min Act: -0.0000

Data Index: 990327 (C4 (Web Text))

Max Activating Token Index: 27

Text #16

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.3151. Min Act: -0.0000

Data Index: 1146401 (C4 (Web Text))

Max Activating Token Index: 234

Text #17

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.3309. Min Act: -0.0000

Data Index: 2646 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.3340. Min Act: -0.0000

Data Index: 1186364 (C4 (Web Text))

Max Activating Token Index: 397

Text #19

Max Range: 0.5485. Min Range: -0.5485

Max Act: 0.3351. Min Act: -0.0000

Data Index: 579732 (C4 (Web Text))

Max Activating Token Index: 545