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

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

Neuron 701 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: 0.2092. Min Range: -0.2092

Max Act: 0.2092. Min Act: -0.0002

Data Index: 1191160 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1898. Min Act: -0.0002

Data Index: 1051258 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1935. Min Act: -0.0002

Data Index: 424215 (C4 (Web Text))

Max Activating Token Index: 1018

Text #3

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1881. Min Act: -0.0002

Data Index: 508578 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1811. Min Act: -0.0002

Data Index: 250390 (C4 (Web Text))

Max Activating Token Index: 438

Text #5

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1769. Min Act: -0.0002

Data Index: 640263 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1865. Min Act: -0.0002

Data Index: 1125561 (C4 (Web Text))

Max Activating Token Index: 249

Text #7

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1948. Min Act: -0.0002

Data Index: 1046453 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1853. Min Act: -0.0002

Data Index: 719805 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1962. Min Act: -0.0002

Data Index: 747097 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1796. Min Act: -0.0002

Data Index: 502339 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1857. Min Act: -0.0002

Data Index: 379044 (C4 (Web Text))

Max Activating Token Index: 82

Text #12

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1813. Min Act: -0.0002

Data Index: 465258 (C4 (Web Text))

Max Activating Token Index: 31

Text #13

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1610. Min Act: -0.0002

Data Index: 1204165 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1757. Min Act: -0.0002

Data Index: 1325565 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1739. Min Act: -0.0002

Data Index: 575487 (C4 (Web Text))

Max Activating Token Index: 433

Text #16

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1823. Min Act: -0.0002

Data Index: 1119419 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1730. Min Act: -0.0002

Data Index: 1150623 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1801. Min Act: -0.0002

Data Index: 488264 (C4 (Web Text))

Max Activating Token Index: 744

Text #19

Max Range: 0.2092. Min Range: -0.2092

Max Act: 0.1787. Min Act: -0.0002

Data Index: 750837 (C4 (Web Text))

Max Activating Token Index: 588