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

Dataset: The Pile

Neuron 2266 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: 0.1753. Min Range: -0.1753

Max Act: 0.1753. Min Act: -0.0000

Data Index: 1814169 (The Pile)

Max Activating Token Index: 1006

Text #1

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1412. Min Act: -0.0001

Data Index: 1842173 (The Pile)

Max Activating Token Index: 180

Text #2

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1484. Min Act: -0.0000

Data Index: 1911115 (The Pile)

Max Activating Token Index: 177

Text #3

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1346. Min Act: -0.0000

Data Index: 1235982 (The Pile)

Max Activating Token Index: 898

Text #4

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1547. Min Act: -0.0000

Data Index: 1596581 (The Pile)

Max Activating Token Index: 799

Text #5

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1343. Min Act: -0.0000

Data Index: 194925 (The Pile)

Max Activating Token Index: 610

Text #6

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1495. Min Act: -0.0000

Data Index: 1303222 (The Pile)

Max Activating Token Index: 455

Text #7

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1268. Min Act: -0.0000

Data Index: 1056004 (The Pile)

Max Activating Token Index: 852

Text #8

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1243. Min Act: -0.0000

Data Index: 998718 (The Pile)

Max Activating Token Index: 960

Text #9

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1261. Min Act: -0.0000

Data Index: 997138 (The Pile)

Max Activating Token Index: 800

Text #10

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1264. Min Act: -0.0000

Data Index: 1554502 (The Pile)

Max Activating Token Index: 550

Text #11

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1210. Min Act: -0.0000

Data Index: 1294581 (The Pile)

Max Activating Token Index: 747

Text #12

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1295. Min Act: -0.0000

Data Index: 1963961 (The Pile)

Max Activating Token Index: 671

Text #13

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1228. Min Act: -0.0001

Data Index: 890546 (The Pile)

Max Activating Token Index: 1010

Text #14

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1185. Min Act: -0.0000

Data Index: 896364 (The Pile)

Max Activating Token Index: 385

Text #15

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1181. Min Act: -0.0000

Data Index: 1853835 (The Pile)

Max Activating Token Index: 48

Text #16

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1197. Min Act: -0.0000

Data Index: 414463 (The Pile)

Max Activating Token Index: 208

Text #17

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1213. Min Act: -0.0001

Data Index: 263600 (The Pile)

Max Activating Token Index: 806

Text #18

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1051. Min Act: -0.0000

Data Index: 1563787 (The Pile)

Max Activating Token Index: 968

Text #19

Max Range: 0.1753. Min Range: -0.1753

Max Act: 0.1130. Min Act: -0.0000

Data Index: 124928 (The Pile)

Max Activating Token Index: 300