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

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

Neuron 2262 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0665. Min Act: -0.0000

Data Index: 1130225 (C4 (Web Text))

Max Activating Token Index: 520

Text #1

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0633. Min Act: -0.0000

Data Index: 1434565 (Python Code)

Max Activating Token Index: 705

Text #2

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0617. Min Act: -0.0000

Data Index: 1305403 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0590. Min Act: -0.0000

Data Index: 1410951 (Python Code)

Max Activating Token Index: 289

Text #4

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0564. Min Act: -0.0000

Data Index: 559717 (C4 (Web Text))

Max Activating Token Index: 397

Text #5

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0584. Min Act: -0.0000

Data Index: 1421297 (Python Code)

Max Activating Token Index: 881

Text #6

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0564. Min Act: -0.0000

Data Index: 1588683 (Python Code)

Max Activating Token Index: 479

Text #7

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0556. Min Act: -0.0000

Data Index: 1488274 (Python Code)

Max Activating Token Index: 247

Text #8

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0510. Min Act: -0.0000

Data Index: 479167 (C4 (Web Text))

Max Activating Token Index: 786

Text #9

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0578. Min Act: -0.0000

Data Index: 1419640 (Python Code)

Max Activating Token Index: 200

Text #10

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0509. Min Act: -0.0000

Data Index: 1044166 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0496. Min Act: -0.0000

Data Index: 765562 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0538. Min Act: -0.0000

Data Index: 1372820 (Python Code)

Max Activating Token Index: 908

Text #13

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0528. Min Act: -0.0000

Data Index: 655140 (C4 (Web Text))

Max Activating Token Index: 314

Text #14

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0533. Min Act: -0.0000

Data Index: 523486 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0502. Min Act: -0.0000

Data Index: 1450386 (Python Code)

Max Activating Token Index: 870

Text #16

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0555. Min Act: -0.0000

Data Index: 267328 (C4 (Web Text))

Max Activating Token Index: 556

Text #17

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0501. Min Act: -0.0000

Data Index: 1646696 (Python Code)

Max Activating Token Index: 1018

Text #18

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0530. Min Act: -0.0000

Data Index: 1420107 (Python Code)

Max Activating Token Index: 881

Text #19

Max Range: 0.0665. Min Range: -0.0665

Max Act: 0.0512. Min Act: -0.0000

Data Index: 1297453 (C4 (Web Text))

Max Activating Token Index: 101