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

Dataset: The Pile

Neuron 4269 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: 1.3763. Min Range: -1.3763

Max Act: 1.3763. Min Act: -0.0000

Data Index: 1559961 (The Pile)

Max Activating Token Index: 845

Text #1

Max Range: 1.3763. Min Range: -1.3763

Max Act: 1.3331. Min Act: -0.0000

Data Index: 611594 (The Pile)

Max Activating Token Index: 881

Text #2

Max Range: 1.3763. Min Range: -1.3763

Max Act: 1.1563. Min Act: -0.0000

Data Index: 822403 (The Pile)

Max Activating Token Index: 423

Text #3

Max Range: 1.3763. Min Range: -1.3763

Max Act: 1.2255. Min Act: -0.0000

Data Index: 299297 (The Pile)

Max Activating Token Index: 681

Text #4

Max Range: 1.3763. Min Range: -1.3763

Max Act: 1.1477. Min Act: -0.0000

Data Index: 1952742 (The Pile)

Max Activating Token Index: 413

Text #5

Max Range: 1.3763. Min Range: -1.3763

Max Act: 1.2031. Min Act: -0.0000

Data Index: 1219910 (The Pile)

Max Activating Token Index: 249

Text #6

Max Range: 1.3763. Min Range: -1.3763

Max Act: 1.1369. Min Act: -0.0000

Data Index: 248468 (The Pile)

Max Activating Token Index: 380

Text #7

Max Range: 1.3763. Min Range: -1.3763

Max Act: 1.1234. Min Act: -0.0000

Data Index: 722662 (The Pile)

Max Activating Token Index: 314

Text #8

Max Range: 1.3763. Min Range: -1.3763

Max Act: 1.1029. Min Act: -0.0000

Data Index: 115903 (The Pile)

Max Activating Token Index: 303

Text #9

Max Range: 1.3763. Min Range: -1.3763

Max Act: 1.1339. Min Act: -0.0000

Data Index: 9445 (The Pile)

Max Activating Token Index: 106

Text #10

Max Range: 1.3763. Min Range: -1.3763

Max Act: 1.0447. Min Act: -0.0000

Data Index: 652804 (The Pile)

Max Activating Token Index: 281

Text #11

Max Range: 1.3763. Min Range: -1.3763

Max Act: 1.0343. Min Act: -0.0000

Data Index: 1517575 (The Pile)

Max Activating Token Index: 828

Text #12

Max Range: 1.3763. Min Range: -1.3763

Max Act: 1.0211. Min Act: -0.0000

Data Index: 1110301 (The Pile)

Max Activating Token Index: 52

Text #13

Max Range: 1.3763. Min Range: -1.3763

Max Act: 0.9542. Min Act: -0.0000

Data Index: 614193 (The Pile)

Max Activating Token Index: 775

Text #14

Max Range: 1.3763. Min Range: -1.3763

Max Act: 1.0056. Min Act: -0.0000

Data Index: 688660 (The Pile)

Max Activating Token Index: 323

Text #15

Max Range: 1.3763. Min Range: -1.3763

Max Act: 1.0104. Min Act: -0.0000

Data Index: 211524 (The Pile)

Max Activating Token Index: 244

Text #16

Max Range: 1.3763. Min Range: -1.3763

Max Act: 0.9380. Min Act: -0.0000

Data Index: 80451 (The Pile)

Max Activating Token Index: 219

Text #17

Max Range: 1.3763. Min Range: -1.3763

Max Act: 0.9512. Min Act: -0.0000

Data Index: 1453109 (The Pile)

Max Activating Token Index: 244

Text #18

Max Range: 1.3763. Min Range: -1.3763

Max Act: 1.0126. Min Act: -0.0000

Data Index: 943080 (The Pile)

Max Activating Token Index: 416

Text #19

Max Range: 1.3763. Min Range: -1.3763

Max Act: 0.9606. Min Act: -0.0000

Data Index: 443022 (The Pile)

Max Activating Token Index: 894