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

Dataset: The Pile

Neuron 2890 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.4369. Min Act: 0.0001

Data Index: 1115805 (The Pile)

Max Activating Token Index: 556

Text #1

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.4359. Min Act: -0.0000

Data Index: 1134942 (The Pile)

Max Activating Token Index: 49

Text #2

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.4431. Min Act: -0.0000

Data Index: 1052621 (The Pile)

Max Activating Token Index: 35

Text #3

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.4188. Min Act: 0.0001

Data Index: 666446 (The Pile)

Max Activating Token Index: 30

Text #4

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3934. Min Act: -0.0000

Data Index: 1536819 (The Pile)

Max Activating Token Index: 692

Text #5

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3682. Min Act: -0.0000

Data Index: 594198 (The Pile)

Max Activating Token Index: 406

Text #6

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3596. Min Act: -0.0000

Data Index: 1533673 (The Pile)

Max Activating Token Index: 151

Text #7

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3538. Min Act: -0.0000

Data Index: 428832 (The Pile)

Max Activating Token Index: 406

Text #8

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3421. Min Act: -0.0000

Data Index: 1748524 (The Pile)

Max Activating Token Index: 604

Text #9

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3354. Min Act: 0.0000

Data Index: 1146719 (The Pile)

Max Activating Token Index: 816

Text #10

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3360. Min Act: 0.0000

Data Index: 1726744 (The Pile)

Max Activating Token Index: 789

Text #11

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3346. Min Act: -0.0000

Data Index: 922261 (The Pile)

Max Activating Token Index: 824

Text #12

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3574. Min Act: -0.0000

Data Index: 1795682 (The Pile)

Max Activating Token Index: 20

Text #13

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3419. Min Act: -0.0000

Data Index: 297372 (The Pile)

Max Activating Token Index: 686

Text #14

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3376. Min Act: -0.0000

Data Index: 48791 (The Pile)

Max Activating Token Index: 581

Text #15

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3480. Min Act: -0.0000

Data Index: 1854915 (The Pile)

Max Activating Token Index: 528

Text #16

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3429. Min Act: -0.0000

Data Index: 199091 (The Pile)

Max Activating Token Index: 447

Text #17

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3457. Min Act: 0.0000

Data Index: 1149709 (The Pile)

Max Activating Token Index: 417

Text #18

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3331. Min Act: -0.0000

Data Index: 1170514 (The Pile)

Max Activating Token Index: 901

Text #19

Max Range: 0.4431. Min Range: -0.4431

Max Act: 0.3317. Min Act: -0.0000

Data Index: 1532863 (The Pile)

Max Activating Token Index: 477