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

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

Neuron 404 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: 0.1824. Min Range: -0.1824

Max Act: 0.1824. Min Act: -0.0001

Data Index: 1198253 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1674. Min Act: -0.0001

Data Index: 48995 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1671. Min Act: -0.0000

Data Index: 222450 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1700. Min Act: -0.0000

Data Index: 425177 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1655. Min Act: -0.0001

Data Index: 646998 (C4 (Web Text))

Max Activating Token Index: 181

Text #5

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1657. Min Act: -0.0000

Data Index: 1053603 (C4 (Web Text))

Max Activating Token Index: 770

Text #6

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1602. Min Act: -0.0000

Data Index: 421725 (C4 (Web Text))

Max Activating Token Index: 197

Text #7

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1484. Min Act: -0.0000

Data Index: 353149 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1579. Min Act: -0.0001

Data Index: 368457 (C4 (Web Text))

Max Activating Token Index: 983

Text #9

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1619. Min Act: -0.0001

Data Index: 748972 (C4 (Web Text))

Max Activating Token Index: 543

Text #10

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1566. Min Act: -0.0001

Data Index: 672719 (C4 (Web Text))

Max Activating Token Index: 444

Text #11

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1656. Min Act: -0.0001

Data Index: 1163566 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1598. Min Act: -0.0000

Data Index: 14607 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1437. Min Act: -0.0000

Data Index: 35594 (C4 (Web Text))

Max Activating Token Index: 217

Text #14

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1562. Min Act: -0.0000

Data Index: 22482 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1495. Min Act: -0.0000

Data Index: 1002205 (C4 (Web Text))

Max Activating Token Index: 374

Text #16

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1534. Min Act: -0.0000

Data Index: 1346645 (C4 (Web Text))

Max Activating Token Index: 210

Text #17

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1536. Min Act: -0.0001

Data Index: 1337866 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1392. Min Act: -0.0000

Data Index: 821573 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 0.1824. Min Range: -0.1824

Max Act: 0.1429. Min Act: -0.0000

Data Index: 310581 (C4 (Web Text))

Max Activating Token Index: 240