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

Dataset: The Pile

Neuron 2701 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: 0.3087. Min Range: -0.3087

Max Act: 0.3087. Min Act: -0.0000

Data Index: 1318712 (The Pile)

Max Activating Token Index: 398

Text #1

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.2579. Min Act: -0.0000

Data Index: 1509344 (The Pile)

Max Activating Token Index: 67

Text #2

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.2124. Min Act: -0.0000

Data Index: 117320 (The Pile)

Max Activating Token Index: 147

Text #3

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.1754. Min Act: -0.0000

Data Index: 580603 (The Pile)

Max Activating Token Index: 360

Text #4

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.1498. Min Act: -0.0000

Data Index: 1944612 (The Pile)

Max Activating Token Index: 92

Text #5

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.1393. Min Act: -0.0000

Data Index: 370396 (The Pile)

Max Activating Token Index: 833

Text #6

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.1435. Min Act: -0.0000

Data Index: 812570 (The Pile)

Max Activating Token Index: 428

Text #7

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.1425. Min Act: -0.0000

Data Index: 1742670 (The Pile)

Max Activating Token Index: 218

Text #8

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.1365. Min Act: -0.0000

Data Index: 1684115 (The Pile)

Max Activating Token Index: 789

Text #9

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.1363. Min Act: -0.0000

Data Index: 1305379 (The Pile)

Max Activating Token Index: 350

Text #10

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.1338. Min Act: -0.0000

Data Index: 612800 (The Pile)

Max Activating Token Index: 47

Text #11

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.1342. Min Act: -0.0000

Data Index: 571760 (The Pile)

Max Activating Token Index: 455

Text #12

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.1366. Min Act: -0.0000

Data Index: 390816 (The Pile)

Max Activating Token Index: 428

Text #13

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.1317. Min Act: -0.0000

Data Index: 1933070 (The Pile)

Max Activating Token Index: 181

Text #14

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.1265. Min Act: -0.0000

Data Index: 1100022 (The Pile)

Max Activating Token Index: 551

Text #15

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.1281. Min Act: -0.0000

Data Index: 48512 (The Pile)

Max Activating Token Index: 404

Text #16

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.1238. Min Act: -0.0000

Data Index: 1502019 (The Pile)

Max Activating Token Index: 100

Text #17

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.1313. Min Act: -0.0000

Data Index: 794389 (The Pile)

Max Activating Token Index: 67

Text #18

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.1266. Min Act: -0.0000

Data Index: 1844149 (The Pile)

Max Activating Token Index: 704

Text #19

Max Range: 0.3087. Min Range: -0.3087

Max Act: 0.1255. Min Act: -0.0000

Data Index: 1755850 (The Pile)

Max Activating Token Index: 584