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

Dataset: The Pile

Neuron 98 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1850. Min Act: -0.0000

Data Index: 1653460 (The Pile)

Max Activating Token Index: 562

Text #1

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1526. Min Act: -0.0000

Data Index: 1737774 (The Pile)

Max Activating Token Index: 978

Text #2

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1471. Min Act: -0.0000

Data Index: 936206 (The Pile)

Max Activating Token Index: 647

Text #3

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1601. Min Act: -0.0000

Data Index: 1463817 (The Pile)

Max Activating Token Index: 104

Text #4

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1387. Min Act: -0.0000

Data Index: 1108975 (The Pile)

Max Activating Token Index: 901

Text #5

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1448. Min Act: -0.0000

Data Index: 1258759 (The Pile)

Max Activating Token Index: 496

Text #6

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1441. Min Act: -0.0000

Data Index: 1267440 (The Pile)

Max Activating Token Index: 910

Text #7

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1418. Min Act: -0.0000

Data Index: 647044 (The Pile)

Max Activating Token Index: 786

Text #8

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1323. Min Act: -0.0000

Data Index: 174471 (The Pile)

Max Activating Token Index: 841

Text #9

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1360. Min Act: -0.0000

Data Index: 582177 (The Pile)

Max Activating Token Index: 33

Text #10

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1409. Min Act: -0.0000

Data Index: 1868287 (The Pile)

Max Activating Token Index: 72

Text #11

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1312. Min Act: -0.0000

Data Index: 1186292 (The Pile)

Max Activating Token Index: 184

Text #12

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1384. Min Act: -0.0000

Data Index: 408762 (The Pile)

Max Activating Token Index: 490

Text #13

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1427. Min Act: -0.0000

Data Index: 612214 (The Pile)

Max Activating Token Index: 345

Text #14

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1359. Min Act: -0.0000

Data Index: 1651639 (The Pile)

Max Activating Token Index: 615

Text #15

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1304. Min Act: -0.0000

Data Index: 953874 (The Pile)

Max Activating Token Index: 283

Text #16

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1329. Min Act: -0.0000

Data Index: 467662 (The Pile)

Max Activating Token Index: 568

Text #17

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1192. Min Act: -0.0000

Data Index: 1570529 (The Pile)

Max Activating Token Index: 223

Text #18

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1268. Min Act: -0.0000

Data Index: 1494910 (The Pile)

Max Activating Token Index: 823

Text #19

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1233. Min Act: -0.0000

Data Index: 247900 (The Pile)

Max Activating Token Index: 948