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

Dataset: The Pile

Neuron 5031 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: 1.3707. Min Range: -1.3707

Max Act: 1.3707. Min Act: -0.0000

Data Index: 1608606 (The Pile)

Max Activating Token Index: 492

Text #1

Max Range: 1.3707. Min Range: -1.3707

Max Act: 1.3211. Min Act: -0.0000

Data Index: 880952 (The Pile)

Max Activating Token Index: 150

Text #2

Max Range: 1.3707. Min Range: -1.3707

Max Act: 1.3048. Min Act: -0.0000

Data Index: 777594 (The Pile)

Max Activating Token Index: 38

Text #3

Max Range: 1.3707. Min Range: -1.3707

Max Act: 1.2562. Min Act: -0.0000

Data Index: 1951964 (The Pile)

Max Activating Token Index: 333

Text #4

Max Range: 1.3707. Min Range: -1.3707

Max Act: 1.3368. Min Act: -0.0000

Data Index: 886748 (The Pile)

Max Activating Token Index: 857

Text #5

Max Range: 1.3707. Min Range: -1.3707

Max Act: 1.2530. Min Act: -0.0000

Data Index: 599404 (The Pile)

Max Activating Token Index: 521

Text #6

Max Range: 1.3707. Min Range: -1.3707

Max Act: 1.2902. Min Act: -0.0000

Data Index: 743709 (The Pile)

Max Activating Token Index: 380

Text #7

Max Range: 1.3707. Min Range: -1.3707

Max Act: 1.1587. Min Act: -0.0000

Data Index: 1812605 (The Pile)

Max Activating Token Index: 83

Text #8

Max Range: 1.3707. Min Range: -1.3707

Max Act: 1.2043. Min Act: -0.0000

Data Index: 1658511 (The Pile)

Max Activating Token Index: 512

Text #9

Max Range: 1.3707. Min Range: -1.3707

Max Act: 1.2848. Min Act: -0.0000

Data Index: 1085905 (The Pile)

Max Activating Token Index: 14

Text #10

Max Range: 1.3707. Min Range: -1.3707

Max Act: 1.1176. Min Act: -0.0000

Data Index: 834759 (The Pile)

Max Activating Token Index: 163

Text #11

Max Range: 1.3707. Min Range: -1.3707

Max Act: 1.1325. Min Act: -0.0000

Data Index: 1789669 (The Pile)

Max Activating Token Index: 293

Text #12

Max Range: 1.3707. Min Range: -1.3707

Max Act: 1.1467. Min Act: -0.0000

Data Index: 1480350 (The Pile)

Max Activating Token Index: 366

Text #13

Max Range: 1.3707. Min Range: -1.3707

Max Act: 1.0591. Min Act: -0.0000

Data Index: 1865533 (The Pile)

Max Activating Token Index: 938

Text #14

Max Range: 1.3707. Min Range: -1.3707

Max Act: 1.1355. Min Act: -0.0000

Data Index: 113477 (The Pile)

Max Activating Token Index: 266

Text #15

Max Range: 1.3707. Min Range: -1.3707

Max Act: 1.0572. Min Act: -0.0000

Data Index: 1956634 (The Pile)

Max Activating Token Index: 474

Text #16

Max Range: 1.3707. Min Range: -1.3707

Max Act: 1.0167. Min Act: -0.0000

Data Index: 650066 (The Pile)

Max Activating Token Index: 146

Text #17

Max Range: 1.3707. Min Range: -1.3707

Max Act: 1.0773. Min Act: -0.0000

Data Index: 848544 (The Pile)

Max Activating Token Index: 129

Text #18

Max Range: 1.3707. Min Range: -1.3707

Max Act: 1.0713. Min Act: -0.0000

Data Index: 1942159 (The Pile)

Max Activating Token Index: 452

Text #19

Max Range: 1.3707. Min Range: -1.3707

Max Act: 1.0311. Min Act: -0.0000

Data Index: 791539 (The Pile)

Max Activating Token Index: 707