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

Dataset: The Pile

Neuron 3674 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.9330. Min Act: -0.0000

Data Index: 1915077 (The Pile)

Max Activating Token Index: 117

Text #1

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.8616. Min Act: -0.0000

Data Index: 1340774 (The Pile)

Max Activating Token Index: 355

Text #2

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.7843. Min Act: -0.0000

Data Index: 1005229 (The Pile)

Max Activating Token Index: 498

Text #3

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.7852. Min Act: -0.0000

Data Index: 1292329 (The Pile)

Max Activating Token Index: 369

Text #4

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.9373. Min Act: -0.0000

Data Index: 1911647 (The Pile)

Max Activating Token Index: 682

Text #5

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.7079. Min Act: -0.0000

Data Index: 967635 (The Pile)

Max Activating Token Index: 219

Text #6

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.7424. Min Act: -0.0000

Data Index: 1185777 (The Pile)

Max Activating Token Index: 802

Text #7

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.5530. Min Act: -0.0000

Data Index: 1196659 (The Pile)

Max Activating Token Index: 289

Text #8

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.6950. Min Act: -0.0000

Data Index: 1768985 (The Pile)

Max Activating Token Index: 29

Text #9

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.5887. Min Act: -0.0000

Data Index: 992888 (The Pile)

Max Activating Token Index: 92

Text #10

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.5595. Min Act: -0.0000

Data Index: 1355417 (The Pile)

Max Activating Token Index: 731

Text #11

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.4497. Min Act: -0.0001

Data Index: 1627971 (The Pile)

Max Activating Token Index: 702

Text #12

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.5482. Min Act: -0.0000

Data Index: 1006462 (The Pile)

Max Activating Token Index: 252

Text #13

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.4501. Min Act: -0.0001

Data Index: 1640500 (The Pile)

Max Activating Token Index: 497

Text #14

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.4835. Min Act: -0.0000

Data Index: 814253 (The Pile)

Max Activating Token Index: 589

Text #15

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.4988. Min Act: -0.0000

Data Index: 1862875 (The Pile)

Max Activating Token Index: 12

Text #16

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.4102. Min Act: -0.0001

Data Index: 1928540 (The Pile)

Max Activating Token Index: 252

Text #17

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.4378. Min Act: -0.0000

Data Index: 834226 (The Pile)

Max Activating Token Index: 691

Text #18

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.3702. Min Act: -0.0000

Data Index: 1033309 (The Pile)

Max Activating Token Index: 523

Text #19

Max Range: 1.9373. Min Range: -1.9373

Max Act: 1.4259. Min Act: -0.0000

Data Index: 1275579 (The Pile)

Max Activating Token Index: 682