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

Dataset: The Pile

Neuron 4639 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: 1.0334. Min Range: -1.0334

Max Act: 1.0173. Min Act: -0.0000

Data Index: 1329956 (The Pile)

Max Activating Token Index: 848

Text #1

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.9425. Min Act: -0.0000

Data Index: 808160 (The Pile)

Max Activating Token Index: 652

Text #2

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.9501. Min Act: -0.0000

Data Index: 1360734 (The Pile)

Max Activating Token Index: 164

Text #3

Max Range: 1.0334. Min Range: -1.0334

Max Act: 1.0334. Min Act: -0.0000

Data Index: 1850811 (The Pile)

Max Activating Token Index: 74

Text #4

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.9220. Min Act: -0.0000

Data Index: 642622 (The Pile)

Max Activating Token Index: 322

Text #5

Max Range: 1.0334. Min Range: -1.0334

Max Act: 1.0029. Min Act: -0.0000

Data Index: 500902 (The Pile)

Max Activating Token Index: 55

Text #6

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.8757. Min Act: -0.0000

Data Index: 569423 (The Pile)

Max Activating Token Index: 181

Text #7

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.8167. Min Act: -0.0000

Data Index: 453271 (The Pile)

Max Activating Token Index: 695

Text #8

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.8533. Min Act: -0.0000

Data Index: 1479463 (The Pile)

Max Activating Token Index: 305

Text #9

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.8679. Min Act: -0.0000

Data Index: 403774 (The Pile)

Max Activating Token Index: 545

Text #10

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.8414. Min Act: -0.0000

Data Index: 60984 (The Pile)

Max Activating Token Index: 147

Text #11

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.7294. Min Act: -0.0000

Data Index: 1550235 (The Pile)

Max Activating Token Index: 497

Text #12

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.8016. Min Act: -0.0000

Data Index: 194577 (The Pile)

Max Activating Token Index: 185

Text #13

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.8361. Min Act: -0.0000

Data Index: 714917 (The Pile)

Max Activating Token Index: 25

Text #14

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.7812. Min Act: -0.0000

Data Index: 932062 (The Pile)

Max Activating Token Index: 632

Text #15

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.7558. Min Act: -0.0000

Data Index: 1009617 (The Pile)

Max Activating Token Index: 81

Text #16

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.7271. Min Act: -0.0000

Data Index: 709417 (The Pile)

Max Activating Token Index: 700

Text #17

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.7821. Min Act: -0.0000

Data Index: 1074165 (The Pile)

Max Activating Token Index: 367

Text #18

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.8344. Min Act: -0.0000

Data Index: 1192162 (The Pile)

Max Activating Token Index: 316

Text #19

Max Range: 1.0334. Min Range: -1.0334

Max Act: 0.7289. Min Act: -0.0000

Data Index: 1750902 (The Pile)

Max Activating Token Index: 361