Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 754 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1713. Min Act: -0.0002

Data Index: 734723 (C4 (Web Text))

Max Activating Token Index: 532

Text #1

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1770. Min Act: -0.0002

Data Index: 155969 (C4 (Web Text))

Max Activating Token Index: 296

Text #2

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1798. Min Act: -0.0002

Data Index: 47024 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1694. Min Act: -0.0002

Data Index: 1159197 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1733. Min Act: -0.0002

Data Index: 670385 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1793. Min Act: -0.0002

Data Index: 532533 (C4 (Web Text))

Max Activating Token Index: 778

Text #6

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1706. Min Act: -0.0002

Data Index: 1208518 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1717. Min Act: -0.0002

Data Index: 1123438 (C4 (Web Text))

Max Activating Token Index: 407

Text #8

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1717. Min Act: -0.0002

Data Index: 355492 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1655. Min Act: -0.0002

Data Index: 221634 (C4 (Web Text))

Max Activating Token Index: 974

Text #10

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1573. Min Act: -0.0002

Data Index: 728628 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1733. Min Act: -0.0002

Data Index: 1253138 (C4 (Web Text))

Max Activating Token Index: 721

Text #12

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1700. Min Act: -0.0002

Data Index: 585563 (C4 (Web Text))

Max Activating Token Index: 442

Text #13

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1633. Min Act: -0.0002

Data Index: 731200 (C4 (Web Text))

Max Activating Token Index: 1010

Text #14

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1677. Min Act: -0.0002

Data Index: 634014 (C4 (Web Text))

Max Activating Token Index: 745

Text #15

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1753. Min Act: -0.0002

Data Index: 1199055 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1657. Min Act: -0.0002

Data Index: 1078059 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1660. Min Act: -0.0002

Data Index: 1331240 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1670. Min Act: -0.0002

Data Index: 1016532 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 0.1798. Min Range: -0.1798

Max Act: 0.1599. Min Act: -0.0002

Data Index: 759552 (C4 (Web Text))

Max Activating Token Index: 427