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

Dataset: The Pile

Neuron 4258 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: 1.1497. Min Range: -1.1497

Max Act: 0.9611. Min Act: -0.0000

Data Index: 225748 (The Pile)

Max Activating Token Index: 413

Text #1

Max Range: 1.1497. Min Range: -1.1497

Max Act: 0.8847. Min Act: -0.0000

Data Index: 1310656 (The Pile)

Max Activating Token Index: 606

Text #2

Max Range: 1.1497. Min Range: -1.1497

Max Act: 0.9714. Min Act: -0.0000

Data Index: 1062596 (The Pile)

Max Activating Token Index: 42

Text #3

Max Range: 1.1497. Min Range: -1.1497

Max Act: 0.9301. Min Act: -0.0000

Data Index: 891453 (The Pile)

Max Activating Token Index: 592

Text #4

Max Range: 1.1497. Min Range: -1.1497

Max Act: 0.9617. Min Act: -0.0000

Data Index: 745171 (The Pile)

Max Activating Token Index: 909

Text #5

Max Range: 1.1497. Min Range: -1.1497

Max Act: 0.8775. Min Act: -0.0000

Data Index: 865681 (The Pile)

Max Activating Token Index: 946

Text #6

Max Range: 1.1497. Min Range: -1.1497

Max Act: 1.1497. Min Act: -0.0000

Data Index: 1937895 (The Pile)

Max Activating Token Index: 985

Text #7

Max Range: 1.1497. Min Range: -1.1497

Max Act: 0.8760. Min Act: -0.0000

Data Index: 1828229 (The Pile)

Max Activating Token Index: 557

Text #8

Max Range: 1.1497. Min Range: -1.1497

Max Act: 0.8813. Min Act: -0.0000

Data Index: 116469 (The Pile)

Max Activating Token Index: 676

Text #9

Max Range: 1.1497. Min Range: -1.1497

Max Act: 0.9287. Min Act: -0.0000

Data Index: 526351 (The Pile)

Max Activating Token Index: 894

Text #10

Max Range: 1.1497. Min Range: -1.1497

Max Act: 0.8621. Min Act: -0.0000

Data Index: 1876840 (The Pile)

Max Activating Token Index: 867

Text #11

Max Range: 1.1497. Min Range: -1.1497

Max Act: 0.9111. Min Act: -0.0000

Data Index: 1167772 (The Pile)

Max Activating Token Index: 866

Text #12

Max Range: 1.1497. Min Range: -1.1497

Max Act: 0.8378. Min Act: -0.0000

Data Index: 454719 (The Pile)

Max Activating Token Index: 329

Text #13

Max Range: 1.1497. Min Range: -1.1497

Max Act: 0.8763. Min Act: -0.0000

Data Index: 1792934 (The Pile)

Max Activating Token Index: 758

Text #14

Max Range: 1.1497. Min Range: -1.1497

Max Act: 0.8352. Min Act: -0.0000

Data Index: 324402 (The Pile)

Max Activating Token Index: 159

Text #15

Max Range: 1.1497. Min Range: -1.1497

Max Act: 0.8462. Min Act: -0.0000

Data Index: 344640 (The Pile)

Max Activating Token Index: 441

Text #16

Max Range: 1.1497. Min Range: -1.1497

Max Act: 0.7823. Min Act: -0.0000

Data Index: 914115 (The Pile)

Max Activating Token Index: 861

Text #17

Max Range: 1.1497. Min Range: -1.1497

Max Act: 0.8571. Min Act: -0.0000

Data Index: 1720226 (The Pile)

Max Activating Token Index: 468

Text #18

Max Range: 1.1497. Min Range: -1.1497

Max Act: 0.7563. Min Act: -0.0000

Data Index: 1625617 (The Pile)

Max Activating Token Index: 566

Text #19

Max Range: 1.1497. Min Range: -1.1497

Max Act: 0.9638. Min Act: -0.0000

Data Index: 1331734 (The Pile)

Max Activating Token Index: 852