Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3997 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.3290. Min Act: -0.0000

Data Index: 143397 (The Pile)

Max Activating Token Index: 897

Text #1

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2738. Min Act: -0.0000

Data Index: 28773 (The Pile)

Max Activating Token Index: 78

Text #2

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2842. Min Act: -0.0000

Data Index: 1718494 (The Pile)

Max Activating Token Index: 506

Text #3

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.3022. Min Act: -0.0000

Data Index: 1575435 (The Pile)

Max Activating Token Index: 65

Text #4

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2816. Min Act: -0.0000

Data Index: 667304 (The Pile)

Max Activating Token Index: 702

Text #5

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2748. Min Act: -0.0000

Data Index: 537669 (The Pile)

Max Activating Token Index: 676

Text #6

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2650. Min Act: -0.0000

Data Index: 398137 (The Pile)

Max Activating Token Index: 462

Text #7

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2622. Min Act: -0.0000

Data Index: 1892326 (The Pile)

Max Activating Token Index: 363

Text #8

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2514. Min Act: -0.0000

Data Index: 1656326 (The Pile)

Max Activating Token Index: 696

Text #9

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2781. Min Act: -0.0000

Data Index: 747178 (The Pile)

Max Activating Token Index: 418

Text #10

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2373. Min Act: -0.0000

Data Index: 23594 (The Pile)

Max Activating Token Index: 683

Text #11

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2558. Min Act: -0.0000

Data Index: 1865896 (The Pile)

Max Activating Token Index: 525

Text #12

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2639. Min Act: -0.0000

Data Index: 1661039 (The Pile)

Max Activating Token Index: 60

Text #13

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2379. Min Act: -0.0000

Data Index: 929968 (The Pile)

Max Activating Token Index: 118

Text #14

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2660. Min Act: -0.0000

Data Index: 201722 (The Pile)

Max Activating Token Index: 23

Text #15

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2410. Min Act: -0.0000

Data Index: 1925002 (The Pile)

Max Activating Token Index: 614

Text #16

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2545. Min Act: -0.0000

Data Index: 395069 (The Pile)

Max Activating Token Index: 188

Text #17

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2432. Min Act: -0.0001

Data Index: 1509058 (The Pile)

Max Activating Token Index: 377

Text #18

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2278. Min Act: -0.0000

Data Index: 833549 (The Pile)

Max Activating Token Index: 661

Text #19

Max Range: 0.3290. Min Range: -0.3290

Max Act: 0.2535. Min Act: -0.0000

Data Index: 1150010 (The Pile)

Max Activating Token Index: 208