Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 34 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.9845. Min Act: -0.0000

Data Index: 1938082 (The Pile)

Max Activating Token Index: 630

Text #1

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.9830. Min Act: -0.0000

Data Index: 1086245 (The Pile)

Max Activating Token Index: 715

Text #2

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.8631. Min Act: -0.0000

Data Index: 1048443 (The Pile)

Max Activating Token Index: 185

Text #3

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.8686. Min Act: -0.0000

Data Index: 648309 (The Pile)

Max Activating Token Index: 195

Text #4

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.8974. Min Act: -0.0000

Data Index: 1491462 (The Pile)

Max Activating Token Index: 312

Text #5

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.8499. Min Act: -0.0000

Data Index: 1472082 (The Pile)

Max Activating Token Index: 644

Text #6

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.8727. Min Act: -0.0000

Data Index: 206695 (The Pile)

Max Activating Token Index: 182

Text #7

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.8393. Min Act: -0.0000

Data Index: 875042 (The Pile)

Max Activating Token Index: 211

Text #8

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.7995. Min Act: -0.0000

Data Index: 1815606 (The Pile)

Max Activating Token Index: 458

Text #9

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.8098. Min Act: -0.0000

Data Index: 1898793 (The Pile)

Max Activating Token Index: 399

Text #10

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.7218. Min Act: -0.0000

Data Index: 807258 (The Pile)

Max Activating Token Index: 546

Text #11

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.7984. Min Act: -0.0000

Data Index: 569763 (The Pile)

Max Activating Token Index: 258

Text #12

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.8277. Min Act: -0.0000

Data Index: 1325524 (The Pile)

Max Activating Token Index: 595

Text #13

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.8157. Min Act: -0.0000

Data Index: 387449 (The Pile)

Max Activating Token Index: 571

Text #14

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.7608. Min Act: -0.0000

Data Index: 736510 (The Pile)

Max Activating Token Index: 617

Text #15

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.7720. Min Act: -0.0000

Data Index: 686210 (The Pile)

Max Activating Token Index: 301

Text #16

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.8004. Min Act: -0.0000

Data Index: 658376 (The Pile)

Max Activating Token Index: 277

Text #17

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.8141. Min Act: -0.0000

Data Index: 588948 (The Pile)

Max Activating Token Index: 937

Text #18

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.8209. Min Act: -0.0000

Data Index: 67173 (The Pile)

Max Activating Token Index: 283

Text #19

Max Range: 0.9845. Min Range: -0.9845

Max Act: 0.7786. Min Act: -0.0000

Data Index: 1078598 (The Pile)

Max Activating Token Index: 200