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

Dataset: The Pile

Neuron 4559 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: 0.2247. Min Range: -0.2247

Max Act: 0.2247. Min Act: -0.0000

Data Index: 1658818 (The Pile)

Max Activating Token Index: 564

Text #1

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1801. Min Act: -0.0000

Data Index: 1876432 (The Pile)

Max Activating Token Index: 508

Text #2

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1864. Min Act: -0.0000

Data Index: 1427297 (The Pile)

Max Activating Token Index: 934

Text #3

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1708. Min Act: -0.0000

Data Index: 1588440 (The Pile)

Max Activating Token Index: 55

Text #4

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1663. Min Act: -0.0000

Data Index: 752995 (The Pile)

Max Activating Token Index: 339

Text #5

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1664. Min Act: -0.0000

Data Index: 1905842 (The Pile)

Max Activating Token Index: 525

Text #6

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1563. Min Act: -0.0000

Data Index: 1630006 (The Pile)

Max Activating Token Index: 27

Text #7

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1685. Min Act: -0.0000

Data Index: 57035 (The Pile)

Max Activating Token Index: 1015

Text #8

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1486. Min Act: -0.0000

Data Index: 88486 (The Pile)

Max Activating Token Index: 439

Text #9

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1533. Min Act: -0.0000

Data Index: 1557350 (The Pile)

Max Activating Token Index: 373

Text #10

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1530. Min Act: -0.0000

Data Index: 862141 (The Pile)

Max Activating Token Index: 97

Text #11

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1549. Min Act: -0.0000

Data Index: 1503531 (The Pile)

Max Activating Token Index: 429

Text #12

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1500. Min Act: -0.0000

Data Index: 1849243 (The Pile)

Max Activating Token Index: 755

Text #13

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1445. Min Act: -0.0000

Data Index: 889511 (The Pile)

Max Activating Token Index: 809

Text #14

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1436. Min Act: -0.0000

Data Index: 1752143 (The Pile)

Max Activating Token Index: 407

Text #15

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1450. Min Act: -0.0000

Data Index: 1613286 (The Pile)

Max Activating Token Index: 424

Text #16

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1581. Min Act: -0.0000

Data Index: 1796637 (The Pile)

Max Activating Token Index: 181

Text #17

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1595. Min Act: -0.0000

Data Index: 133946 (The Pile)

Max Activating Token Index: 179

Text #18

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1421. Min Act: -0.0000

Data Index: 1690948 (The Pile)

Max Activating Token Index: 702

Text #19

Max Range: 0.2247. Min Range: -0.2247

Max Act: 0.1521. Min Act: -0.0000

Data Index: 1673352 (The Pile)

Max Activating Token Index: 522