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

Dataset: The Pile

Neuron 2984 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: 0.2525. Min Range: -0.2525

Max Act: 0.2525. Min Act: -0.0000

Data Index: 40736 (The Pile)

Max Activating Token Index: 222

Text #1

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.2001. Min Act: -0.0000

Data Index: 501443 (The Pile)

Max Activating Token Index: 82

Text #2

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1849. Min Act: -0.0000

Data Index: 1093144 (The Pile)

Max Activating Token Index: 606

Text #3

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1812. Min Act: -0.0000

Data Index: 1302372 (The Pile)

Max Activating Token Index: 98

Text #4

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1502. Min Act: -0.0000

Data Index: 423122 (The Pile)

Max Activating Token Index: 626

Text #5

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1432. Min Act: -0.0000

Data Index: 1579795 (The Pile)

Max Activating Token Index: 155

Text #6

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1582. Min Act: -0.0000

Data Index: 1521392 (The Pile)

Max Activating Token Index: 325

Text #7

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1530. Min Act: -0.0000

Data Index: 1638581 (The Pile)

Max Activating Token Index: 924

Text #8

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1496. Min Act: -0.0000

Data Index: 1024527 (The Pile)

Max Activating Token Index: 550

Text #9

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1514. Min Act: -0.0000

Data Index: 107533 (The Pile)

Max Activating Token Index: 978

Text #10

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1381. Min Act: -0.0000

Data Index: 427656 (The Pile)

Max Activating Token Index: 653

Text #11

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1414. Min Act: -0.0000

Data Index: 1462761 (The Pile)

Max Activating Token Index: 407

Text #12

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1421. Min Act: -0.0000

Data Index: 497300 (The Pile)

Max Activating Token Index: 506

Text #13

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1382. Min Act: -0.0000

Data Index: 1218294 (The Pile)

Max Activating Token Index: 605

Text #14

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1245. Min Act: -0.0000

Data Index: 12873 (The Pile)

Max Activating Token Index: 325

Text #15

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1240. Min Act: -0.0000

Data Index: 1897308 (The Pile)

Max Activating Token Index: 67

Text #16

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1279. Min Act: -0.0000

Data Index: 1401576 (The Pile)

Max Activating Token Index: 375

Text #17

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1229. Min Act: -0.0000

Data Index: 23773 (The Pile)

Max Activating Token Index: 365

Text #18

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1330. Min Act: -0.0000

Data Index: 711381 (The Pile)

Max Activating Token Index: 274

Text #19

Max Range: 0.2525. Min Range: -0.2525

Max Act: 0.1272. Min Act: -0.0000

Data Index: 1574713 (The Pile)

Max Activating Token Index: 327