Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2606 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.2040. Min Act: -0.0000

Data Index: 1609399 (Python Code)

Max Activating Token Index: 855

Text #1

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1716. Min Act: -0.0000

Data Index: 309615 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1596. Min Act: -0.0000

Data Index: 682917 (C4 (Web Text))

Max Activating Token Index: 864

Text #3

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1626. Min Act: -0.0000

Data Index: 476333 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1711. Min Act: -0.0000

Data Index: 1147694 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1695. Min Act: -0.0000

Data Index: 228813 (C4 (Web Text))

Max Activating Token Index: 609

Text #6

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1691. Min Act: -0.0000

Data Index: 380854 (C4 (Web Text))

Max Activating Token Index: 492

Text #7

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1549. Min Act: -0.0000

Data Index: 971106 (C4 (Web Text))

Max Activating Token Index: 206

Text #8

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1656. Min Act: -0.0000

Data Index: 1107529 (C4 (Web Text))

Max Activating Token Index: 282

Text #9

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1577. Min Act: -0.0000

Data Index: 1644279 (Python Code)

Max Activating Token Index: 426

Text #10

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1563. Min Act: -0.0000

Data Index: 1644376 (Python Code)

Max Activating Token Index: 10

Text #11

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1600. Min Act: -0.0000

Data Index: 1274242 (C4 (Web Text))

Max Activating Token Index: 768

Text #12

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1479. Min Act: -0.0000

Data Index: 756953 (C4 (Web Text))

Max Activating Token Index: 972

Text #13

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1644. Min Act: -0.0000

Data Index: 245205 (C4 (Web Text))

Max Activating Token Index: 559

Text #14

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1686. Min Act: -0.0000

Data Index: 608986 (C4 (Web Text))

Max Activating Token Index: 362

Text #15

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1359. Min Act: -0.0000

Data Index: 661964 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1505. Min Act: -0.0000

Data Index: 355642 (C4 (Web Text))

Max Activating Token Index: 577

Text #17

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1487. Min Act: -0.0000

Data Index: 1498622 (Python Code)

Max Activating Token Index: 451

Text #18

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1597. Min Act: -0.0000

Data Index: 550899 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 0.2040. Min Range: -0.2040

Max Act: 0.1479. Min Act: -0.0000

Data Index: 969413 (C4 (Web Text))

Max Activating Token Index: 48