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

Dataset: The Pile

Neuron 1710 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.7486. Min Act: -0.0000

Data Index: 454306 (The Pile)

Max Activating Token Index: 956

Text #1

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.6815. Min Act: -0.0000

Data Index: 1542326 (The Pile)

Max Activating Token Index: 15

Text #2

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.6690. Min Act: -0.0000

Data Index: 1212160 (The Pile)

Max Activating Token Index: 976

Text #3

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.4621. Min Act: -0.0000

Data Index: 472718 (The Pile)

Max Activating Token Index: 742

Text #4

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.5565. Min Act: -0.0000

Data Index: 1653343 (The Pile)

Max Activating Token Index: 5

Text #5

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.6332. Min Act: -0.0000

Data Index: 1944515 (The Pile)

Max Activating Token Index: 584

Text #6

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.4252. Min Act: -0.0000

Data Index: 275775 (The Pile)

Max Activating Token Index: 323

Text #7

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.2316. Min Act: -0.0000

Data Index: 644670 (The Pile)

Max Activating Token Index: 950

Text #8

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.4990. Min Act: -0.0000

Data Index: 263788 (The Pile)

Max Activating Token Index: 854

Text #9

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.4335. Min Act: -0.0000

Data Index: 52623 (The Pile)

Max Activating Token Index: 676

Text #10

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.1239. Min Act: -0.0000

Data Index: 944958 (The Pile)

Max Activating Token Index: 419

Text #11

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.2319. Min Act: -0.0000

Data Index: 289538 (The Pile)

Max Activating Token Index: 538

Text #12

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.1990. Min Act: -0.0000

Data Index: 1718343 (The Pile)

Max Activating Token Index: 620

Text #13

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.0444. Min Act: -0.0000

Data Index: 219251 (The Pile)

Max Activating Token Index: 892

Text #14

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.1691. Min Act: -0.0000

Data Index: 338457 (The Pile)

Max Activating Token Index: 867

Text #15

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.1675. Min Act: -0.0000

Data Index: 604285 (The Pile)

Max Activating Token Index: 1000

Text #16

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.1958. Min Act: -0.0000

Data Index: 409798 (The Pile)

Max Activating Token Index: 919

Text #17

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.1721. Min Act: -0.0000

Data Index: 667587 (The Pile)

Max Activating Token Index: 602

Text #18

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.1427. Min Act: -0.0000

Data Index: 496896 (The Pile)

Max Activating Token Index: 604

Text #19

Max Range: 3.7486. Min Range: -3.7486

Max Act: 3.1316. Min Act: -0.0000

Data Index: 1734970 (The Pile)

Max Activating Token Index: 13