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

Dataset: The Pile

Neuron 3966 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7326. Min Range: -3.7326

Max Act: 3.2044. Min Act: -0.0000

Data Index: 1002991 (The Pile)

Max Activating Token Index: 618

Text #1

Max Range: 3.7326. Min Range: -3.7326

Max Act: 3.7326. Min Act: -0.0000

Data Index: 595205 (The Pile)

Max Activating Token Index: 198

Text #2

Max Range: 3.7326. Min Range: -3.7326

Max Act: 3.5358. Min Act: -0.0000

Data Index: 799251 (The Pile)

Max Activating Token Index: 12

Text #3

Max Range: 3.7326. Min Range: -3.7326

Max Act: 3.2644. Min Act: -0.0000

Data Index: 809138 (The Pile)

Max Activating Token Index: 384

Text #4

Max Range: 3.7326. Min Range: -3.7326

Max Act: 3.4141. Min Act: -0.0000

Data Index: 1743245 (The Pile)

Max Activating Token Index: 370

Text #5

Max Range: 3.7326. Min Range: -3.7326

Max Act: 3.6716. Min Act: -0.0000

Data Index: 1938447 (The Pile)

Max Activating Token Index: 742

Text #6

Max Range: 3.7326. Min Range: -3.7326

Max Act: 3.2605. Min Act: -0.0000

Data Index: 842436 (The Pile)

Max Activating Token Index: 642

Text #7

Max Range: 3.7326. Min Range: -3.7326

Max Act: 3.1096. Min Act: -0.0000

Data Index: 1853564 (The Pile)

Max Activating Token Index: 555

Text #8

Max Range: 3.7326. Min Range: -3.7326

Max Act: 3.2122. Min Act: -0.0000

Data Index: 828237 (The Pile)

Max Activating Token Index: 307

Text #9

Max Range: 3.7326. Min Range: -3.7326

Max Act: 3.3306. Min Act: -0.0000

Data Index: 687384 (The Pile)

Max Activating Token Index: 413

Text #10

Max Range: 3.7326. Min Range: -3.7326

Max Act: 3.0274. Min Act: -0.0000

Data Index: 1865961 (The Pile)

Max Activating Token Index: 164

Text #11

Max Range: 3.7326. Min Range: -3.7326

Max Act: 3.0554. Min Act: -0.0000

Data Index: 571867 (The Pile)

Max Activating Token Index: 69

Text #12

Max Range: 3.7326. Min Range: -3.7326

Max Act: 3.1396. Min Act: -0.0000

Data Index: 197848 (The Pile)

Max Activating Token Index: 701

Text #13

Max Range: 3.7326. Min Range: -3.7326

Max Act: 2.8500. Min Act: -0.0000

Data Index: 671561 (The Pile)

Max Activating Token Index: 358

Text #14

Max Range: 3.7326. Min Range: -3.7326

Max Act: 3.1258. Min Act: -0.0000

Data Index: 1254351 (The Pile)

Max Activating Token Index: 451

Text #15

Max Range: 3.7326. Min Range: -3.7326

Max Act: 3.1025. Min Act: -0.0000

Data Index: 925654 (The Pile)

Max Activating Token Index: 300

Text #16

Max Range: 3.7326. Min Range: -3.7326

Max Act: 2.9483. Min Act: -0.0000

Data Index: 1941573 (The Pile)

Max Activating Token Index: 199

Text #17

Max Range: 3.7326. Min Range: -3.7326

Max Act: 2.9362. Min Act: -0.0000

Data Index: 911615 (The Pile)

Max Activating Token Index: 64

Text #18

Max Range: 3.7326. Min Range: -3.7326

Max Act: 3.0647. Min Act: -0.0000

Data Index: 1829793 (The Pile)

Max Activating Token Index: 857

Text #19

Max Range: 3.7326. Min Range: -3.7326

Max Act: 3.0351. Min Act: -0.0000

Data Index: 668468 (The Pile)

Max Activating Token Index: 404