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

Dataset: The Pile

Neuron 2265 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: 0.3405. Min Range: -0.3405

Max Act: 0.3047. Min Act: -0.0000

Data Index: 875639 (The Pile)

Max Activating Token Index: 221

Text #1

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2862. Min Act: -0.0000

Data Index: 584175 (The Pile)

Max Activating Token Index: 159

Text #2

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2768. Min Act: -0.0000

Data Index: 398680 (The Pile)

Max Activating Token Index: 350

Text #3

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.3405. Min Act: -0.0000

Data Index: 53841 (The Pile)

Max Activating Token Index: 332

Text #4

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.3016. Min Act: -0.0000

Data Index: 1700965 (The Pile)

Max Activating Token Index: 342

Text #5

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2813. Min Act: -0.0000

Data Index: 946474 (The Pile)

Max Activating Token Index: 810

Text #6

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.3025. Min Act: -0.0000

Data Index: 1984553 (The Pile)

Max Activating Token Index: 422

Text #7

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2805. Min Act: -0.0000

Data Index: 1370766 (The Pile)

Max Activating Token Index: 958

Text #8

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2535. Min Act: -0.0000

Data Index: 1635499 (The Pile)

Max Activating Token Index: 796

Text #9

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2864. Min Act: -0.0000

Data Index: 1648614 (The Pile)

Max Activating Token Index: 730

Text #10

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.3039. Min Act: -0.0000

Data Index: 833220 (The Pile)

Max Activating Token Index: 792

Text #11

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2534. Min Act: -0.0000

Data Index: 1022798 (The Pile)

Max Activating Token Index: 132

Text #12

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2603. Min Act: -0.0000

Data Index: 1891207 (The Pile)

Max Activating Token Index: 373

Text #13

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2441. Min Act: -0.0000

Data Index: 721263 (The Pile)

Max Activating Token Index: 357

Text #14

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2329. Min Act: -0.0000

Data Index: 1751181 (The Pile)

Max Activating Token Index: 130

Text #15

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2391. Min Act: -0.0000

Data Index: 1673218 (The Pile)

Max Activating Token Index: 306

Text #16

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2544. Min Act: -0.0000

Data Index: 1407170 (The Pile)

Max Activating Token Index: 125

Text #17

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2477. Min Act: -0.0000

Data Index: 343580 (The Pile)

Max Activating Token Index: 752

Text #18

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2298. Min Act: -0.0000

Data Index: 741603 (The Pile)

Max Activating Token Index: 594

Text #19

Max Range: 0.3405. Min Range: -0.3405

Max Act: 0.2275. Min Act: -0.0000

Data Index: 667497 (The Pile)

Max Activating Token Index: 456