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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 648 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1869. Min Act: -0.0000

Data Index: 1108676 (C4 (Web Text))

Max Activating Token Index: 232

Text #1

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1711. Min Act: -0.0000

Data Index: 479110 (C4 (Web Text))

Max Activating Token Index: 979

Text #2

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1759. Min Act: -0.0000

Data Index: 1249513 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1668. Min Act: -0.0000

Data Index: 543432 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1595. Min Act: -0.0000

Data Index: 1098146 (C4 (Web Text))

Max Activating Token Index: 894

Text #5

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1557. Min Act: -0.0000

Data Index: 709977 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1534. Min Act: -0.0000

Data Index: 185675 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1654. Min Act: -0.0000

Data Index: 372610 (C4 (Web Text))

Max Activating Token Index: 357

Text #8

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1670. Min Act: -0.0000

Data Index: 1340446 (C4 (Web Text))

Max Activating Token Index: 920

Text #9

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1351. Min Act: -0.0000

Data Index: 267851 (C4 (Web Text))

Max Activating Token Index: 540

Text #10

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1519. Min Act: -0.0000

Data Index: 695863 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1439. Min Act: -0.0000

Data Index: 1070050 (C4 (Web Text))

Max Activating Token Index: 559

Text #12

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1560. Min Act: -0.0000

Data Index: 748590 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1551. Min Act: -0.0000

Data Index: 663704 (C4 (Web Text))

Max Activating Token Index: 164

Text #14

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1591. Min Act: -0.0000

Data Index: 1142359 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1533. Min Act: -0.0000

Data Index: 489272 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1483. Min Act: -0.0000

Data Index: 62720 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1461. Min Act: -0.0000

Data Index: 26274 (C4 (Web Text))

Max Activating Token Index: 359

Text #18

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1460. Min Act: -0.0000

Data Index: 734960 (C4 (Web Text))

Max Activating Token Index: 291

Text #19

Max Range: 0.1869. Min Range: -0.1869

Max Act: 0.1503. Min Act: -0.0000

Data Index: 1230654 (C4 (Web Text))

Max Activating Token Index: 208