Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2119 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1975. Min Act: -0.0001

Data Index: 746187 (C4 (Web Text))

Max Activating Token Index: 577

Text #1

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.2047. Min Act: -0.0001

Data Index: 468162 (C4 (Web Text))

Max Activating Token Index: 486

Text #2

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1923. Min Act: -0.0001

Data Index: 755616 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1825. Min Act: -0.0001

Data Index: 1410140 (Python Code)

Max Activating Token Index: 263

Text #4

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1851. Min Act: -0.0001

Data Index: 1486520 (Python Code)

Max Activating Token Index: 472

Text #5

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1898. Min Act: -0.0001

Data Index: 1467014 (Python Code)

Max Activating Token Index: 562

Text #6

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1911. Min Act: -0.0001

Data Index: 1431320 (Python Code)

Max Activating Token Index: 513

Text #7

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1951. Min Act: -0.0001

Data Index: 1510585 (Python Code)

Max Activating Token Index: 815

Text #8

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1691. Min Act: -0.0001

Data Index: 1558141 (Python Code)

Max Activating Token Index: 723

Text #9

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1821. Min Act: -0.0001

Data Index: 1013785 (C4 (Web Text))

Max Activating Token Index: 301

Text #10

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1770. Min Act: -0.0001

Data Index: 1644624 (Python Code)

Max Activating Token Index: 18

Text #11

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1627. Min Act: -0.0001

Data Index: 103257 (C4 (Web Text))

Max Activating Token Index: 516

Text #12

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1618. Min Act: -0.0001

Data Index: 319114 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1863. Min Act: -0.0001

Data Index: 19940 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1657. Min Act: -0.0001

Data Index: 562966 (C4 (Web Text))

Max Activating Token Index: 205

Text #15

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1669. Min Act: -0.0001

Data Index: 789217 (C4 (Web Text))

Max Activating Token Index: 767

Text #16

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1787. Min Act: -0.0001

Data Index: 1638895 (Python Code)

Max Activating Token Index: 460

Text #17

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1594. Min Act: -0.0001

Data Index: 1598161 (Python Code)

Max Activating Token Index: 338

Text #18

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1699. Min Act: -0.0001

Data Index: 1553077 (Python Code)

Max Activating Token Index: 604

Text #19

Max Range: 0.2047. Min Range: -0.2047

Max Act: 0.1745. Min Act: -0.0001

Data Index: 1636785 (Python Code)

Max Activating Token Index: 699