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

Dataset: The Pile

Neuron 4671 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.3520. Min Act: -0.0000

Data Index: 358364 (The Pile)

Max Activating Token Index: 689

Text #1

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.3394. Min Act: -0.0000

Data Index: 839154 (The Pile)

Max Activating Token Index: 591

Text #2

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.3396. Min Act: -0.0000

Data Index: 864616 (The Pile)

Max Activating Token Index: 70

Text #3

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2962. Min Act: -0.0000

Data Index: 425304 (The Pile)

Max Activating Token Index: 41

Text #4

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.3094. Min Act: -0.0000

Data Index: 410443 (The Pile)

Max Activating Token Index: 830

Text #5

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.3155. Min Act: -0.0000

Data Index: 1507460 (The Pile)

Max Activating Token Index: 845

Text #6

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2973. Min Act: -0.0000

Data Index: 584786 (The Pile)

Max Activating Token Index: 324

Text #7

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2672. Min Act: -0.0000

Data Index: 887231 (The Pile)

Max Activating Token Index: 354

Text #8

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2780. Min Act: -0.0000

Data Index: 363727 (The Pile)

Max Activating Token Index: 20

Text #9

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2624. Min Act: -0.0000

Data Index: 1861204 (The Pile)

Max Activating Token Index: 480

Text #10

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2754. Min Act: -0.0000

Data Index: 1500854 (The Pile)

Max Activating Token Index: 113

Text #11

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2646. Min Act: -0.0000

Data Index: 1297606 (The Pile)

Max Activating Token Index: 174

Text #12

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2584. Min Act: -0.0000

Data Index: 813613 (The Pile)

Max Activating Token Index: 722

Text #13

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2713. Min Act: -0.0000

Data Index: 1127654 (The Pile)

Max Activating Token Index: 482

Text #14

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2705. Min Act: -0.0000

Data Index: 62867 (The Pile)

Max Activating Token Index: 490

Text #15

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2311. Min Act: -0.0000

Data Index: 1197660 (The Pile)

Max Activating Token Index: 496

Text #16

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2542. Min Act: -0.0000

Data Index: 1392652 (The Pile)

Max Activating Token Index: 211

Text #17

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2696. Min Act: -0.0000

Data Index: 208620 (The Pile)

Max Activating Token Index: 138

Text #18

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2290. Min Act: -0.0000

Data Index: 1768509 (The Pile)

Max Activating Token Index: 118

Text #19

Max Range: 0.3520. Min Range: -0.3520

Max Act: 0.2598. Min Act: -0.0000

Data Index: 888902 (The Pile)

Max Activating Token Index: 52