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

Dataset: The Pile

Neuron 3120 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: 0.4344. Min Range: -0.4344

Max Act: 0.4344. Min Act: -0.0000

Data Index: 816909 (The Pile)

Max Activating Token Index: 457

Text #1

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.3641. Min Act: -0.0000

Data Index: 221455 (The Pile)

Max Activating Token Index: 769

Text #2

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.3242. Min Act: -0.0000

Data Index: 1750086 (The Pile)

Max Activating Token Index: 931

Text #3

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.3286. Min Act: -0.0000

Data Index: 1562645 (The Pile)

Max Activating Token Index: 506

Text #4

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.2672. Min Act: -0.0000

Data Index: 907932 (The Pile)

Max Activating Token Index: 205

Text #5

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.2950. Min Act: -0.0000

Data Index: 1226897 (The Pile)

Max Activating Token Index: 764

Text #6

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.2660. Min Act: -0.0000

Data Index: 656532 (The Pile)

Max Activating Token Index: 632

Text #7

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.2526. Min Act: -0.0000

Data Index: 1461535 (The Pile)

Max Activating Token Index: 796

Text #8

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.2924. Min Act: -0.0000

Data Index: 1921315 (The Pile)

Max Activating Token Index: 882

Text #9

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.2743. Min Act: -0.0000

Data Index: 1508056 (The Pile)

Max Activating Token Index: 718

Text #10

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.2382. Min Act: -0.0000

Data Index: 1902011 (The Pile)

Max Activating Token Index: 823

Text #11

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.2472. Min Act: -0.0000

Data Index: 307603 (The Pile)

Max Activating Token Index: 553

Text #12

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.3092. Min Act: -0.0000

Data Index: 190239 (The Pile)

Max Activating Token Index: 63

Text #13

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.2688. Min Act: -0.0000

Data Index: 509495 (The Pile)

Max Activating Token Index: 403

Text #14

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.2482. Min Act: -0.0000

Data Index: 896357 (The Pile)

Max Activating Token Index: 706

Text #15

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.2480. Min Act: -0.0000

Data Index: 729535 (The Pile)

Max Activating Token Index: 694

Text #16

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.2420. Min Act: -0.0000

Data Index: 564350 (The Pile)

Max Activating Token Index: 401

Text #17

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.2491. Min Act: -0.0000

Data Index: 1516421 (The Pile)

Max Activating Token Index: 517

Text #18

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.2485. Min Act: -0.0000

Data Index: 921185 (The Pile)

Max Activating Token Index: 512

Text #19

Max Range: 0.4344. Min Range: -0.4344

Max Act: 0.2287. Min Act: -0.0000

Data Index: 147431 (The Pile)

Max Activating Token Index: 906