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

Dataset: The Pile

Neuron 3998 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: 0.3035. Min Range: -0.3035

Max Act: 0.3035. Min Act: -0.0000

Data Index: 342600 (The Pile)

Max Activating Token Index: 671

Text #1

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2774. Min Act: -0.0000

Data Index: 1362254 (The Pile)

Max Activating Token Index: 729

Text #2

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2593. Min Act: -0.0000

Data Index: 1991501 (The Pile)

Max Activating Token Index: 559

Text #3

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2609. Min Act: -0.0000

Data Index: 282746 (The Pile)

Max Activating Token Index: 814

Text #4

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2783. Min Act: -0.0000

Data Index: 1061970 (The Pile)

Max Activating Token Index: 141

Text #5

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2650. Min Act: -0.0000

Data Index: 883615 (The Pile)

Max Activating Token Index: 44

Text #6

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2565. Min Act: -0.0000

Data Index: 1811216 (The Pile)

Max Activating Token Index: 778

Text #7

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2606. Min Act: -0.0000

Data Index: 1250554 (The Pile)

Max Activating Token Index: 553

Text #8

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2369. Min Act: -0.0000

Data Index: 18847 (The Pile)

Max Activating Token Index: 759

Text #9

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2504. Min Act: -0.0000

Data Index: 45478 (The Pile)

Max Activating Token Index: 940

Text #10

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2504. Min Act: -0.0000

Data Index: 1718810 (The Pile)

Max Activating Token Index: 112

Text #11

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2493. Min Act: -0.0000

Data Index: 357821 (The Pile)

Max Activating Token Index: 987

Text #12

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2345. Min Act: -0.0000

Data Index: 1828010 (The Pile)

Max Activating Token Index: 857

Text #13

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2627. Min Act: -0.0000

Data Index: 1849912 (The Pile)

Max Activating Token Index: 295

Text #14

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2676. Min Act: -0.0000

Data Index: 1542622 (The Pile)

Max Activating Token Index: 750

Text #15

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2517. Min Act: -0.0000

Data Index: 78377 (The Pile)

Max Activating Token Index: 429

Text #16

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2288. Min Act: -0.0000

Data Index: 1096335 (The Pile)

Max Activating Token Index: 847

Text #17

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2373. Min Act: -0.0000

Data Index: 584724 (The Pile)

Max Activating Token Index: 504

Text #18

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2301. Min Act: -0.0000

Data Index: 672982 (The Pile)

Max Activating Token Index: 814

Text #19

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2469. Min Act: -0.0000

Data Index: 165651 (The Pile)

Max Activating Token Index: 450