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

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

Neuron 3214 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1851. Min Act: -0.0001

Data Index: 740315 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1554. Min Act: -0.0001

Data Index: 107965 (C4 (Web Text))

Max Activating Token Index: 707

Text #2

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1655. Min Act: -0.0001

Data Index: 909769 (C4 (Web Text))

Max Activating Token Index: 310

Text #3

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1571. Min Act: -0.0001

Data Index: 1196881 (C4 (Web Text))

Max Activating Token Index: 911

Text #4

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1506. Min Act: -0.0001

Data Index: 830273 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1534. Min Act: -0.0001

Data Index: 707833 (C4 (Web Text))

Max Activating Token Index: 144

Text #6

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1451. Min Act: -0.0001

Data Index: 617410 (C4 (Web Text))

Max Activating Token Index: 1021

Text #7

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1610. Min Act: -0.0001

Data Index: 1202956 (C4 (Web Text))

Max Activating Token Index: 1007

Text #8

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1401. Min Act: -0.0001

Data Index: 167514 (C4 (Web Text))

Max Activating Token Index: 326

Text #9

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1623. Min Act: -0.0001

Data Index: 655137 (C4 (Web Text))

Max Activating Token Index: 756

Text #10

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1557. Min Act: -0.0001

Data Index: 314598 (C4 (Web Text))

Max Activating Token Index: 606

Text #11

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1678. Min Act: -0.0001

Data Index: 316499 (C4 (Web Text))

Max Activating Token Index: 849

Text #12

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1509. Min Act: -0.0001

Data Index: 1247281 (C4 (Web Text))

Max Activating Token Index: 847

Text #13

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1443. Min Act: -0.0001

Data Index: 64851 (C4 (Web Text))

Max Activating Token Index: 775

Text #14

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1445. Min Act: -0.0001

Data Index: 1065355 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1633. Min Act: -0.0001

Data Index: 1030983 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1381. Min Act: -0.0001

Data Index: 1150583 (C4 (Web Text))

Max Activating Token Index: 466

Text #17

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1412. Min Act: -0.0001

Data Index: 391880 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1485. Min Act: -0.0001

Data Index: 308992 (C4 (Web Text))

Max Activating Token Index: 608

Text #19

Max Range: 0.1851. Min Range: -0.1851

Max Act: 0.1554. Min Act: -0.0001

Data Index: 146921 (C4 (Web Text))

Max Activating Token Index: 498