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

Dataset: The Pile

Neuron 3335 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9193. Min Range: -5.9193

Max Act: 5.9193. Min Act: 0.0001

Data Index: 643714 (The Pile)

Max Activating Token Index: 535

Text #1

Max Range: 5.9193. Min Range: -5.9193

Max Act: 3.4797. Min Act: -0.0000

Data Index: 1532182 (The Pile)

Max Activating Token Index: 193

Text #2

Max Range: 5.9193. Min Range: -5.9193

Max Act: 4.4123. Min Act: 0.0000

Data Index: 607925 (The Pile)

Max Activating Token Index: 854

Text #3

Max Range: 5.9193. Min Range: -5.9193

Max Act: 3.8778. Min Act: -0.0000

Data Index: 1190705 (The Pile)

Max Activating Token Index: 1010

Text #4

Max Range: 5.9193. Min Range: -5.9193

Max Act: 4.0716. Min Act: -0.0000

Data Index: 1074130 (The Pile)

Max Activating Token Index: 677

Text #5

Max Range: 5.9193. Min Range: -5.9193

Max Act: 3.6322. Min Act: -0.0000

Data Index: 1985260 (The Pile)

Max Activating Token Index: 592

Text #6

Max Range: 5.9193. Min Range: -5.9193

Max Act: 3.6146. Min Act: -0.0000

Data Index: 1636604 (The Pile)

Max Activating Token Index: 216

Text #7

Max Range: 5.9193. Min Range: -5.9193

Max Act: 3.1927. Min Act: -0.0000

Data Index: 882505 (The Pile)

Max Activating Token Index: 437

Text #8

Max Range: 5.9193. Min Range: -5.9193

Max Act: 3.7226. Min Act: -0.0000

Data Index: 840747 (The Pile)

Max Activating Token Index: 542

Text #9

Max Range: 5.9193. Min Range: -5.9193

Max Act: 3.1201. Min Act: 0.0000

Data Index: 1060690 (The Pile)

Max Activating Token Index: 808

Text #10

Max Range: 5.9193. Min Range: -5.9193

Max Act: 3.2382. Min Act: 0.0000

Data Index: 1529738 (The Pile)

Max Activating Token Index: 362

Text #11

Max Range: 5.9193. Min Range: -5.9193

Max Act: 3.2473. Min Act: -0.0000

Data Index: 1638039 (The Pile)

Max Activating Token Index: 197

Text #12

Max Range: 5.9193. Min Range: -5.9193

Max Act: 3.0581. Min Act: -0.0000

Data Index: 732125 (The Pile)

Max Activating Token Index: 411

Text #13

Max Range: 5.9193. Min Range: -5.9193

Max Act: 3.2088. Min Act: -0.0000

Data Index: 143047 (The Pile)

Max Activating Token Index: 390

Text #14

Max Range: 5.9193. Min Range: -5.9193

Max Act: 3.0444. Min Act: -0.0000

Data Index: 1122436 (The Pile)

Max Activating Token Index: 613

Text #15

Max Range: 5.9193. Min Range: -5.9193

Max Act: 3.1570. Min Act: -0.0000

Data Index: 1117151 (The Pile)

Max Activating Token Index: 600

Text #16

Max Range: 5.9193. Min Range: -5.9193

Max Act: 3.0317. Min Act: -0.0000

Data Index: 651424 (The Pile)

Max Activating Token Index: 679

Text #17

Max Range: 5.9193. Min Range: -5.9193

Max Act: 3.1323. Min Act: -0.0000

Data Index: 27454 (The Pile)

Max Activating Token Index: 527

Text #18

Max Range: 5.9193. Min Range: -5.9193

Max Act: 2.9713. Min Act: -0.0000

Data Index: 1251860 (The Pile)

Max Activating Token Index: 841

Text #19

Max Range: 5.9193. Min Range: -5.9193

Max Act: 3.1217. Min Act: 0.0000

Data Index: 1130449 (The Pile)

Max Activating Token Index: 48