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

Dataset: The Pile

Neuron 3614 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: 1.0478. Min Range: -1.0478

Max Act: 1.0478. Min Act: -0.0000

Data Index: 392020 (The Pile)

Max Activating Token Index: 419

Text #1

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.8242. Min Act: -0.0000

Data Index: 1644187 (The Pile)

Max Activating Token Index: 67

Text #2

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.8385. Min Act: -0.0000

Data Index: 791015 (The Pile)

Max Activating Token Index: 49

Text #3

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.8436. Min Act: -0.0000

Data Index: 684126 (The Pile)

Max Activating Token Index: 277

Text #4

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.7736. Min Act: -0.0000

Data Index: 660069 (The Pile)

Max Activating Token Index: 426

Text #5

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.7446. Min Act: -0.0000

Data Index: 1715989 (The Pile)

Max Activating Token Index: 22

Text #6

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.6940. Min Act: -0.0000

Data Index: 116485 (The Pile)

Max Activating Token Index: 160

Text #7

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.7305. Min Act: -0.0000

Data Index: 541080 (The Pile)

Max Activating Token Index: 17

Text #8

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.7275. Min Act: -0.0000

Data Index: 1712003 (The Pile)

Max Activating Token Index: 978

Text #9

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.7681. Min Act: -0.0000

Data Index: 542293 (The Pile)

Max Activating Token Index: 183

Text #10

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.7076. Min Act: -0.0000

Data Index: 762512 (The Pile)

Max Activating Token Index: 59

Text #11

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.7242. Min Act: -0.0000

Data Index: 1912775 (The Pile)

Max Activating Token Index: 161

Text #12

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.6848. Min Act: -0.0000

Data Index: 1377855 (The Pile)

Max Activating Token Index: 357

Text #13

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.7401. Min Act: -0.0001

Data Index: 743706 (The Pile)

Max Activating Token Index: 45

Text #14

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.7358. Min Act: -0.0000

Data Index: 1301987 (The Pile)

Max Activating Token Index: 439

Text #15

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.7300. Min Act: -0.0000

Data Index: 1946471 (The Pile)

Max Activating Token Index: 94

Text #16

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.7343. Min Act: -0.0000

Data Index: 1528282 (The Pile)

Max Activating Token Index: 587

Text #17

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.7074. Min Act: -0.0000

Data Index: 1410927 (The Pile)

Max Activating Token Index: 380

Text #18

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.6614. Min Act: -0.0000

Data Index: 1845541 (The Pile)

Max Activating Token Index: 335

Text #19

Max Range: 1.0478. Min Range: -1.0478

Max Act: 0.6820. Min Act: -0.0000

Data Index: 272057 (The Pile)

Max Activating Token Index: 207