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

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

Neuron 1711 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1729. Min Act: -0.0002

Data Index: 274274 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1739. Min Act: -0.0002

Data Index: 1477 (C4 (Web Text))

Max Activating Token Index: 74

Text #2

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1767. Min Act: -0.0002

Data Index: 110331 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1545. Min Act: -0.0002

Data Index: 838618 (C4 (Web Text))

Max Activating Token Index: 867

Text #4

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1725. Min Act: -0.0002

Data Index: 1279321 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1669. Min Act: -0.0002

Data Index: 483725 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1588. Min Act: -0.0002

Data Index: 1147146 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1511. Min Act: -0.0002

Data Index: 74757 (C4 (Web Text))

Max Activating Token Index: 879

Text #8

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1620. Min Act: -0.0002

Data Index: 947283 (C4 (Web Text))

Max Activating Token Index: 726

Text #9

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1517. Min Act: -0.0002

Data Index: 952773 (C4 (Web Text))

Max Activating Token Index: 76

Text #10

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1479. Min Act: -0.0002

Data Index: 545969 (C4 (Web Text))

Max Activating Token Index: 206

Text #11

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1481. Min Act: -0.0002

Data Index: 743730 (C4 (Web Text))

Max Activating Token Index: 985

Text #12

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1500. Min Act: -0.0002

Data Index: 159334 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1559. Min Act: -0.0002

Data Index: 1268222 (C4 (Web Text))

Max Activating Token Index: 814

Text #14

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1604. Min Act: -0.0002

Data Index: 677780 (C4 (Web Text))

Max Activating Token Index: 616

Text #15

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1467. Min Act: -0.0002

Data Index: 992613 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1472. Min Act: -0.0002

Data Index: 641822 (C4 (Web Text))

Max Activating Token Index: 631

Text #17

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1456. Min Act: -0.0002

Data Index: 423913 (C4 (Web Text))

Max Activating Token Index: 861

Text #18

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1410. Min Act: -0.0002

Data Index: 92569 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 0.1767. Min Range: -0.1767

Max Act: 0.1461. Min Act: -0.0002

Data Index: 509652 (C4 (Web Text))

Max Activating Token Index: 177