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

Dataset: The Pile

Neuron 784 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.2171. Min Act: -0.0000

Data Index: 1374414 (The Pile)

Max Activating Token Index: 678

Text #1

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1825. Min Act: -0.0000

Data Index: 1118216 (The Pile)

Max Activating Token Index: 56

Text #2

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1621. Min Act: -0.0000

Data Index: 1303205 (The Pile)

Max Activating Token Index: 496

Text #3

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1594. Min Act: -0.0000

Data Index: 48846 (The Pile)

Max Activating Token Index: 521

Text #4

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1695. Min Act: -0.0000

Data Index: 1730207 (The Pile)

Max Activating Token Index: 263

Text #5

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1469. Min Act: -0.0000

Data Index: 920053 (The Pile)

Max Activating Token Index: 46

Text #6

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1492. Min Act: -0.0000

Data Index: 1105104 (The Pile)

Max Activating Token Index: 756

Text #7

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1329. Min Act: -0.0000

Data Index: 852639 (The Pile)

Max Activating Token Index: 852

Text #8

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1466. Min Act: -0.0000

Data Index: 127973 (The Pile)

Max Activating Token Index: 56

Text #9

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1391. Min Act: -0.0000

Data Index: 367676 (The Pile)

Max Activating Token Index: 123

Text #10

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1506. Min Act: -0.0000

Data Index: 1753904 (The Pile)

Max Activating Token Index: 701

Text #11

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1422. Min Act: -0.0000

Data Index: 558660 (The Pile)

Max Activating Token Index: 475

Text #12

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1356. Min Act: -0.0000

Data Index: 1604580 (The Pile)

Max Activating Token Index: 634

Text #13

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1404. Min Act: -0.0000

Data Index: 1011136 (The Pile)

Max Activating Token Index: 68

Text #14

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1397. Min Act: -0.0000

Data Index: 1938075 (The Pile)

Max Activating Token Index: 350

Text #15

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1284. Min Act: -0.0000

Data Index: 1550974 (The Pile)

Max Activating Token Index: 373

Text #16

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1536. Min Act: -0.0000

Data Index: 1311443 (The Pile)

Max Activating Token Index: 995

Text #17

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1315. Min Act: -0.0000

Data Index: 1425954 (The Pile)

Max Activating Token Index: 468

Text #18

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1372. Min Act: -0.0000

Data Index: 1172983 (The Pile)

Max Activating Token Index: 650

Text #19

Max Range: 0.2171. Min Range: -0.2171

Max Act: 0.1344. Min Act: -0.0000

Data Index: 1230059 (The Pile)

Max Activating Token Index: 956