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

Dataset: The Pile

Neuron 4796 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: 1.4383. Min Range: -1.4383

Max Act: 1.4383. Min Act: -0.0000

Data Index: 1594359 (The Pile)

Max Activating Token Index: 128

Text #1

Max Range: 1.4383. Min Range: -1.4383

Max Act: 1.1385. Min Act: 0.0000

Data Index: 1338801 (The Pile)

Max Activating Token Index: 220

Text #2

Max Range: 1.4383. Min Range: -1.4383

Max Act: 1.1534. Min Act: -0.0000

Data Index: 1020527 (The Pile)

Max Activating Token Index: 477

Text #3

Max Range: 1.4383. Min Range: -1.4383

Max Act: 1.1536. Min Act: -0.0000

Data Index: 1746954 (The Pile)

Max Activating Token Index: 805

Text #4

Max Range: 1.4383. Min Range: -1.4383

Max Act: 1.1141. Min Act: 0.0000

Data Index: 1182857 (The Pile)

Max Activating Token Index: 613

Text #5

Max Range: 1.4383. Min Range: -1.4383

Max Act: 1.1106. Min Act: -0.0000

Data Index: 1859850 (The Pile)

Max Activating Token Index: 361

Text #6

Max Range: 1.4383. Min Range: -1.4383

Max Act: 1.0885. Min Act: -0.0000

Data Index: 742969 (The Pile)

Max Activating Token Index: 994

Text #7

Max Range: 1.4383. Min Range: -1.4383

Max Act: 0.9820. Min Act: -0.0000

Data Index: 259499 (The Pile)

Max Activating Token Index: 440

Text #8

Max Range: 1.4383. Min Range: -1.4383

Max Act: 1.0881. Min Act: -0.0000

Data Index: 575108 (The Pile)

Max Activating Token Index: 222

Text #9

Max Range: 1.4383. Min Range: -1.4383

Max Act: 1.0131. Min Act: -0.0000

Data Index: 1856482 (The Pile)

Max Activating Token Index: 583

Text #10

Max Range: 1.4383. Min Range: -1.4383

Max Act: 0.9389. Min Act: 0.0000

Data Index: 1264569 (The Pile)

Max Activating Token Index: 283

Text #11

Max Range: 1.4383. Min Range: -1.4383

Max Act: 0.9777. Min Act: -0.0000

Data Index: 1932672 (The Pile)

Max Activating Token Index: 540

Text #12

Max Range: 1.4383. Min Range: -1.4383

Max Act: 0.9724. Min Act: -0.0000

Data Index: 1750402 (The Pile)

Max Activating Token Index: 141

Text #13

Max Range: 1.4383. Min Range: -1.4383

Max Act: 0.9267. Min Act: -0.0000

Data Index: 229740 (The Pile)

Max Activating Token Index: 959

Text #14

Max Range: 1.4383. Min Range: -1.4383

Max Act: 0.9645. Min Act: -0.0000

Data Index: 1631069 (The Pile)

Max Activating Token Index: 96

Text #15

Max Range: 1.4383. Min Range: -1.4383

Max Act: 0.9511. Min Act: 0.0000

Data Index: 714149 (The Pile)

Max Activating Token Index: 87

Text #16

Max Range: 1.4383. Min Range: -1.4383

Max Act: 0.9542. Min Act: -0.0000

Data Index: 1062318 (The Pile)

Max Activating Token Index: 793

Text #17

Max Range: 1.4383. Min Range: -1.4383

Max Act: 0.9491. Min Act: -0.0000

Data Index: 525619 (The Pile)

Max Activating Token Index: 283

Text #18

Max Range: 1.4383. Min Range: -1.4383

Max Act: 0.9990. Min Act: -0.0000

Data Index: 744516 (The Pile)

Max Activating Token Index: 561

Text #19

Max Range: 1.4383. Min Range: -1.4383

Max Act: 0.8559. Min Act: -0.0000

Data Index: 501397 (The Pile)

Max Activating Token Index: 1023